Abstract Artificial learners often behave differently from human learners in the context of neural agent-based simulations of language emergence and change. A common explanation is the lack of appropriate cognitive biases in these learners. However, it has also been proposed that more naturalistic settings of language learning and use could lead to more human-like results. We investigate this latter account, focusing on the word-order/case-marking trade-off, a widely attested language universal that has proven particularly hard to simulate. We propose a new Neural-agent Language Learning and Communication framework (NeLLCom) where pairs of speaking and listening agents first learn a miniature language via supervised learning, and then optimize it for communication via reinforcement learning. Following closely the setup of earlier human experiments, we succeed in replicating the trade-off with the new framework without hard-coding specific biases in the agents. We see this as an essential step towards the investigation of language universals with neural learners.
{"title":"Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-off","authors":"Yuchen Lian, Arianna Bisazza, T. Verhoef","doi":"10.1162/tacl_a_00587","DOIUrl":"https://doi.org/10.1162/tacl_a_00587","url":null,"abstract":"Abstract Artificial learners often behave differently from human learners in the context of neural agent-based simulations of language emergence and change. A common explanation is the lack of appropriate cognitive biases in these learners. However, it has also been proposed that more naturalistic settings of language learning and use could lead to more human-like results. We investigate this latter account, focusing on the word-order/case-marking trade-off, a widely attested language universal that has proven particularly hard to simulate. We propose a new Neural-agent Language Learning and Communication framework (NeLLCom) where pairs of speaking and listening agents first learn a miniature language via supervised learning, and then optimize it for communication via reinforcement learning. Following closely the setup of earlier human experiments, we succeed in replicating the trade-off with the new framework without hard-coding specific biases in the agents. We see this as an essential step towards the investigation of language universals with neural learners.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"11 1","pages":"1033-1047"},"PeriodicalIF":10.9,"publicationDate":"2023-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43044930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xudong Hong, A. Sayeed, K. Mehra, Vera Demberg, B. Schiele
Current work on image-based story generation suffers from the fact that the existing image sequence collections do not have coherent plots behind them. We improve visual story generation by producing a new image-grounded dataset, Visual Writing Prompts (VWP). VWP contains almost 2K selected sequences of movie shots, each including 5-10 images. The image sequences are aligned with a total of 12K stories which were collected via crowdsourcing given the image sequences and a set of grounded characters from the corresponding image sequence. Our new image sequence collection and filtering process has allowed us to obtain stories that are more coherent, diverse, and visually grounded compared to previous work. We also propose a character-based story generation model driven by coherence as a strong baseline. Evaluations show that our generated stories are more coherent, visually grounded, and diverse than stories generated with the current state-of-the-art model. Our code, image features, annotations and collected stories are available at https://vwprompt.github.io/.
{"title":"Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences","authors":"Xudong Hong, A. Sayeed, K. Mehra, Vera Demberg, B. Schiele","doi":"10.1162/tacl_a_00553","DOIUrl":"https://doi.org/10.1162/tacl_a_00553","url":null,"abstract":"Current work on image-based story generation suffers from the fact that the existing image sequence collections do not have coherent plots behind them. We improve visual story generation by producing a new image-grounded dataset, Visual Writing Prompts (VWP). VWP contains almost 2K selected sequences of movie shots, each including 5-10 images. The image sequences are aligned with a total of 12K stories which were collected via crowdsourcing given the image sequences and a set of grounded characters from the corresponding image sequence. Our new image sequence collection and filtering process has allowed us to obtain stories that are more coherent, diverse, and visually grounded compared to previous work. We also propose a character-based story generation model driven by coherence as a strong baseline. Evaluations show that our generated stories are more coherent, visually grounded, and diverse than stories generated with the current state-of-the-art model. Our code, image features, annotations and collected stories are available at https://vwprompt.github.io/.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"11 1","pages":"565-581"},"PeriodicalIF":10.9,"publicationDate":"2023-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45975746","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Neural sequence generation models are known to “hallucinate”, by producing outputs that are unrelated to the source text. These hallucinations are potentially harmful, yet it remains unclear in what conditions they arise and how to mitigate their impact. In this work, we first identify internal model symptoms of hallucinations by analyzing the relative token contributions to the generation in contrastive hallucinated vs. non-hallucinated outputs generated via source perturbations. We then show that these symptoms are reliable indicators of natural hallucinations, by using them to design a lightweight hallucination detector which outperforms both model-free baselines and strong classifiers based on quality estimation or large pre-trained models on manually annotated English-Chinese and German-English translation test beds.
{"title":"Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection","authors":"Weijia Xu, Sweta Agrawal, Eleftheria Briakou, Marianna J. Martindale, Marine Carpuat","doi":"10.1162/tacl_a_00563","DOIUrl":"https://doi.org/10.1162/tacl_a_00563","url":null,"abstract":"Neural sequence generation models are known to “hallucinate”, by producing outputs that are unrelated to the source text. These hallucinations are potentially harmful, yet it remains unclear in what conditions they arise and how to mitigate their impact. In this work, we first identify internal model symptoms of hallucinations by analyzing the relative token contributions to the generation in contrastive hallucinated vs. non-hallucinated outputs generated via source perturbations. We then show that these symptoms are reliable indicators of natural hallucinations, by using them to design a lightweight hallucination detector which outperforms both model-free baselines and strong classifiers based on quality estimation or large pre-trained models on manually annotated English-Chinese and German-English translation test beds.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"11 1","pages":"546-564"},"PeriodicalIF":10.9,"publicationDate":"2023-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48824724","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Monitoring online customer reviews is important for business organizations to measure customer satisfaction and better manage their reputations. In this paper, we propose a novel dynamic Brand-Topic Model (dBTM) which is able to automatically detect and track brand-associated sentiment scores and polarity-bearing topics from product reviews organized in temporally ordered time intervals. dBTM models the evolution of the latent brand polarity scores and the topic-word distributions over time by Gaussian state space models. It also incorporates a meta learning strategy to control the update of the topic-word distribution in each time interval in order to ensure smooth topic transitions and better brand score predictions. It has been evaluated on a dataset constructed from MakeupAlley reviews and a hotel review dataset. Experimental results show that dBTM outperforms a number of competitive baselines in brand ranking, achieving a good balance of topic coherence and uniqueness, and extracting well-separated polarity-bearing topics across time intervals.1
{"title":"Tracking Brand-Associated Polarity-Bearing Topics in User Reviews","authors":"Runcong Zhao, Lin Gui, Hanqi Yan, Yulan He","doi":"10.1162/tacl_a_00555","DOIUrl":"https://doi.org/10.1162/tacl_a_00555","url":null,"abstract":"Monitoring online customer reviews is important for business organizations to measure customer satisfaction and better manage their reputations. In this paper, we propose a novel dynamic Brand-Topic Model (dBTM) which is able to automatically detect and track brand-associated sentiment scores and polarity-bearing topics from product reviews organized in temporally ordered time intervals. dBTM models the evolution of the latent brand polarity scores and the topic-word distributions over time by Gaussian state space models. It also incorporates a meta learning strategy to control the update of the topic-word distribution in each time interval in order to ensure smooth topic transitions and better brand score predictions. It has been evaluated on a dataset constructed from MakeupAlley reviews and a hotel review dataset. Experimental results show that dBTM outperforms a number of competitive baselines in brand ranking, achieving a good balance of topic coherence and uniqueness, and extracting well-separated polarity-bearing topics across time intervals.1","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"11 1","pages":"404-418"},"PeriodicalIF":10.9,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47444673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Named Entity Recognition (NER) has so far evolved from the traditional flat NER to overlapped and discontinuous NER. They have mostly been solved separately, with only several exceptions that concurrently tackle three tasks with a single model. The current best-performing method formalizes the unified NER as word-word relation classification, which barely focuses on mention content learning and fails to detect entity mentions comprising a single word. In this paper, we propose a two-stage span-based framework with templates, namely, T2-NER, to resolve the unified NER task. The first stage is to extract entity spans, where flat and overlapped entities can be recognized. The second stage is to classify over all entity span pairs, where discontinuous entities can be recognized. Finally, multi-task learning is used to jointly train two stages. To improve the efficiency of span-based model, we design grouped templates and typed templates for two stages to realize batch computations. We also apply an adjacent packing strategy and a latter packing strategy to model discriminative boundary information and learn better span (pair) representation. Moreover, we introduce the syntax information to enhance our span representation. We perform extensive experiments on eight benchmark datasets for flat, overlapped, and discontinuous NER, where our model beats all the current competitive baselines, obtaining the best performance of unified NER.
{"title":"<i>T</i> 2 <i>-NER</i>: A <u>T</u>wo-Stage Span-Based Framework for Unified Named Entity Recognition with <u>T</u>emplates","authors":"Peixin Huang, Xiang Zhao, Minghao Hu, Zhen Tan, Weidong Xiao","doi":"10.1162/tacl_a_00602","DOIUrl":"https://doi.org/10.1162/tacl_a_00602","url":null,"abstract":"Abstract Named Entity Recognition (NER) has so far evolved from the traditional flat NER to overlapped and discontinuous NER. They have mostly been solved separately, with only several exceptions that concurrently tackle three tasks with a single model. The current best-performing method formalizes the unified NER as word-word relation classification, which barely focuses on mention content learning and fails to detect entity mentions comprising a single word. In this paper, we propose a two-stage span-based framework with templates, namely, T2-NER, to resolve the unified NER task. The first stage is to extract entity spans, where flat and overlapped entities can be recognized. The second stage is to classify over all entity span pairs, where discontinuous entities can be recognized. Finally, multi-task learning is used to jointly train two stages. To improve the efficiency of span-based model, we design grouped templates and typed templates for two stages to realize batch computations. We also apply an adjacent packing strategy and a latter packing strategy to model discriminative boundary information and learn better span (pair) representation. Moreover, we introduce the syntax information to enhance our span representation. We perform extensive experiments on eight benchmark datasets for flat, overlapped, and discontinuous NER, where our model beats all the current competitive baselines, obtaining the best performance of unified NER.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135057751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract The events in a narrative are understood as a coherent whole via the underlying states of their participants. Often, these participant states are not explicitly mentioned, instead left to be inferred by the reader. A model that understands narratives should likewise infer these implicit states, and even reason about the impact of changes to these states on the narrative. To facilitate this goal, we introduce a new crowdsourced English-language, Participant States dataset, PASTA. This dataset contains inferable participant states; a counterfactual perturbation to each state; and the changes to the story that would be necessary if the counterfactual were true. We introduce three state-based reasoning tasks that test for the ability to infer when a state is entailed by a story, to revise a story conditioned on a counterfactual state, and to explain the most likely state change given a revised story. Experiments show that today’s LLMs can reason about states to some degree, but there is large room for improvement, especially in problems requiring access and ability to reason with diverse types of knowledge (e.g., physical, numerical, factual).1
{"title":"<tt>PASTA</tt>: A Dataset for Modeling PArticipant STAtes in Narratives","authors":"Sayontan Ghosh, Mahnaz Koupaee, Isabella Chen, Francis Ferraro, Nathanael Chambers, Niranjan Balasubramanian","doi":"10.1162/tacl_a_00600","DOIUrl":"https://doi.org/10.1162/tacl_a_00600","url":null,"abstract":"Abstract The events in a narrative are understood as a coherent whole via the underlying states of their participants. Often, these participant states are not explicitly mentioned, instead left to be inferred by the reader. A model that understands narratives should likewise infer these implicit states, and even reason about the impact of changes to these states on the narrative. To facilitate this goal, we introduce a new crowdsourced English-language, Participant States dataset, PASTA. This dataset contains inferable participant states; a counterfactual perturbation to each state; and the changes to the story that would be necessary if the counterfactual were true. We introduce three state-based reasoning tasks that test for the ability to infer when a state is entailed by a story, to revise a story conditioned on a counterfactual state, and to explain the most likely state change given a revised story. Experiments show that today’s LLMs can reason about states to some degree, but there is large room for improvement, especially in problems requiring access and ability to reason with diverse types of knowledge (e.g., physical, numerical, factual).1","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135560520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Sequence generation models are increasingly being used to translate natural language into programs, i.e., to perform executable semantic parsing. The fact that semantic parsing aims to predict programs that can lead to executed actions in the real world motivates developing safe systems. This in turn makes measuring calibration—a central component to safety—particularly important. We investigate the calibration of popular generation models across four popular semantic parsing datasets, finding that it varies across models and datasets. We then analyze factors associated with calibration error and release new confidence-based challenge splits of two parsing datasets. To facilitate the inclusion of calibration in semantic parsing evaluations, we release a library for computing calibration metrics.1
{"title":"Calibrated Interpretation: Confidence Estimation in Semantic Parsing","authors":"Elias Stengel-Eskin, Benjamin Van Durme","doi":"10.1162/tacl_a_00598","DOIUrl":"https://doi.org/10.1162/tacl_a_00598","url":null,"abstract":"Abstract Sequence generation models are increasingly being used to translate natural language into programs, i.e., to perform executable semantic parsing. The fact that semantic parsing aims to predict programs that can lead to executed actions in the real world motivates developing safe systems. This in turn makes measuring calibration—a central component to safety—particularly important. We investigate the calibration of popular generation models across four popular semantic parsing datasets, finding that it varies across models and datasets. We then analyze factors associated with calibration error and release new confidence-based challenge splits of two parsing datasets. To facilitate the inclusion of calibration in semantic parsing evaluations, we release a library for computing calibration metrics.1","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135911382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wenzheng Zhang, Chenyan Xiong, Karl Stratos, Arnold Overwijk
Abstract In multitask retrieval, a single retriever is trained to retrieve relevant contexts for multiple tasks. Despite its practical appeal, naive multitask retrieval lags behind task-specific retrieval, in which a separate retriever is trained for each task. We show that it is possible to train a multitask retriever that outperforms task-specific retrievers by promoting task specialization. The main ingredients are: (1) a better choice of pretrained model—one that is explicitly optimized for multitasking—along with compatible prompting, and (2) a novel adaptive learning method that encourages each parameter to specialize in a particular task. The resulting multitask retriever is highly performant on the KILT benchmark. Upon analysis, we find that the model indeed learns parameters that are more task-specialized compared to naive multitasking without prompting or adaptive learning.1
{"title":"Improving Multitask Retrieval by Promoting Task Specialization","authors":"Wenzheng Zhang, Chenyan Xiong, Karl Stratos, Arnold Overwijk","doi":"10.1162/tacl_a_00597","DOIUrl":"https://doi.org/10.1162/tacl_a_00597","url":null,"abstract":"Abstract In multitask retrieval, a single retriever is trained to retrieve relevant contexts for multiple tasks. Despite its practical appeal, naive multitask retrieval lags behind task-specific retrieval, in which a separate retriever is trained for each task. We show that it is possible to train a multitask retriever that outperforms task-specific retrievers by promoting task specialization. The main ingredients are: (1) a better choice of pretrained model—one that is explicitly optimized for multitasking—along with compatible prompting, and (2) a novel adaptive learning method that encourages each parameter to specialize in a particular task. The resulting multitask retriever is highly performant on the KILT benchmark. Upon analysis, we find that the model indeed learns parameters that are more task-specialized compared to naive multitasking without prompting or adaptive learning.1","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135699919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Daniel Russo, Serra Sinem Tekiroğlu, Marco Guerini
Abstract Fighting misinformation is a challenging, yet crucial, task. Despite the growing number of experts being involved in manual fact-checking, this activity is time-consuming and cannot keep up with the ever-increasing amount of fake news produced daily. Hence, automating this process is necessary to help curb misinformation. Thus far, researchers have mainly focused on claim veracity classification. In this paper, instead, we address the generation of justifications (textual explanation of why a claim is classified as either true or false) and benchmark it with novel datasets and advanced baselines. In particular, we focus on summarization approaches over unstructured knowledge (i.e., news articles) and we experiment with several extractive and abstractive strategies. We employed two datasets with different styles and structures, in order to assess the generalizability of our findings. Results show that in justification production summarization benefits from the claim information, and, in particular, that a claim-driven extractive step improves abstractive summarization performances. Finally, we show that although cross-dataset experiments suffer from performance degradation, a unique model trained on a combination of the two datasets is able to retain style information in an efficient manner.
{"title":"Benchmarking the Generation of Fact Checking Explanations","authors":"Daniel Russo, Serra Sinem Tekiroğlu, Marco Guerini","doi":"10.1162/tacl_a_00601","DOIUrl":"https://doi.org/10.1162/tacl_a_00601","url":null,"abstract":"Abstract Fighting misinformation is a challenging, yet crucial, task. Despite the growing number of experts being involved in manual fact-checking, this activity is time-consuming and cannot keep up with the ever-increasing amount of fake news produced daily. Hence, automating this process is necessary to help curb misinformation. Thus far, researchers have mainly focused on claim veracity classification. In this paper, instead, we address the generation of justifications (textual explanation of why a claim is classified as either true or false) and benchmark it with novel datasets and advanced baselines. In particular, we focus on summarization approaches over unstructured knowledge (i.e., news articles) and we experiment with several extractive and abstractive strategies. We employed two datasets with different styles and structures, in order to assess the generalizability of our findings. Results show that in justification production summarization benefits from the claim information, and, in particular, that a claim-driven extractive step improves abstractive summarization performances. Finally, we show that although cross-dataset experiments suffer from performance degradation, a unique model trained on a combination of the two datasets is able to retain style information in an efficient manner.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135057750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
William Dyer, Charles Torres, Gregory Scontras, Richard Futrell
Abstract The literature on adjective ordering abounds with proposals meant to account for why certain adjectives appear before others in multi-adjective strings (e.g., the small brown box). However, these proposals have been developed and tested primarily in isolation and based on English; few researchers have looked at the combined performance of multiple factors in the determination of adjective order, and few have evaluated predictors across multiple languages. The current work approaches both of these objectives by using technologies and datasets from natural language processing to look at the combined performance of existing proposals across 32 languages. Comparing this performance with both random and idealized baselines, we show that the literature on adjective ordering has made significant meaningful progress across its many decades, but there remains quite a gap yet to be explained.
{"title":"Evaluating a Century of Progress on the Cognitive Science of Adjective Ordering","authors":"William Dyer, Charles Torres, Gregory Scontras, Richard Futrell","doi":"10.1162/tacl_a_00596","DOIUrl":"https://doi.org/10.1162/tacl_a_00596","url":null,"abstract":"Abstract The literature on adjective ordering abounds with proposals meant to account for why certain adjectives appear before others in multi-adjective strings (e.g., the small brown box). However, these proposals have been developed and tested primarily in isolation and based on English; few researchers have looked at the combined performance of multiple factors in the determination of adjective order, and few have evaluated predictors across multiple languages. The current work approaches both of these objectives by using technologies and datasets from natural language processing to look at the combined performance of existing proposals across 32 languages. Comparing this performance with both random and idealized baselines, we show that the literature on adjective ordering has made significant meaningful progress across its many decades, but there remains quite a gap yet to be explained.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135596936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：