Reading the Manual: Event Extraction as Definition Comprehension

Chen, Yunmo; Chen, Tongfei; Ebner, Seth; White, Aaron Steven; Durme, Benjamin Van

doi:10.18653/v1/2020.spnlp-1.9

Cited by 40 publications

(20 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chen et al [45] use bleached statements giving models acquire to information included in annotation manuals. Du et al [7] apply machine reading comprehension method employs event extraction and enhance data by constructing multiple question for each argument.…”

Section: Comparisonsmentioning

confidence: 99%

Reinforcement Learning-Based Dialogue Guided Event Extraction to Exploit Argument Relations

Peng

et al. 2022

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Event extraction is a fundamental task for natural language processing. Finding the roles of event arguments like event participants is essential for event extraction. However, doing so for real-life event descriptions is challenging because an argument's role often varies in different contexts. While the relationship and interactions between multiple arguments are useful for settling the argument roles, such information is largely ignored by existing approaches. This paper presents a better approach for event extraction by explicitly utilizing the relationships of event arguments. We achieve this through a carefully designed task-oriented dialogue system. To model the argument relation, we employ reinforcement learning and incremental learning to extract multiple arguments via a multiturned, iterative process. Our approach leverages knowledge of the already extracted arguments of the same sentence to determine the role of arguments that would be difficult to decide individually. It then uses the newly obtained information to improve the decisions of previously extracted arguments. This twoway feedback process allows us to exploit the argument relations to effectively settle argument roles, leading to better sentence understanding and event extraction. Experimental results show that our approach consistently outperforms seven state-of-theart event extraction methods for the classification of events and argument role and argument identification.

show abstract

Section: Comparisonsmentioning

confidence: 99%

Reinforcement Learning-Based Dialogue Guided Event Extraction to Exploit Argument Relations

Peng

et al. 2022

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…t ← TRUTHPREDICTOR(y) 13: P ← P ∪ (@truth, t) 14: return P 15: end function Single subsection We follow the paradigm of Chen et al (2020), where we iteratively modify the text of the subsection by inserting argument values, and predict values for uninstantiated arguments. Throughout the following, we refer to Algorithm 1 and to its notation.…”

Section: Algorithm 1 Argument Instantiation For a Single Subsectionmentioning

confidence: 99%

“…We concatenate the text of the case c with the modified text of the subsection r, and embed it using BERT (line 5), yielding a sequence of contextual subword embeddings y = {y i ∈ R 768 | i = 1...n}. Keeping with the notation of Chen et al (2020), assume that the embedded case is represented by the sequence of vectors t 1 , ..., t m and the embedded subsection by s 1 , ..., s n . For a given argument a, compute its attentive representations 1 , ...,s m and its augmented feature vectors x 1 , ..., x m .…”

Section: Algorithm 1 Argument Instantiation For a Single Subsectionmentioning

confidence: 99%

“…For a given argument a, compute its attentive representations 1 , ...,s m and its augmented feature vectors x 1 , ..., x m . This operation, described by Chen et al (2020), is performed by COMPUTEATTENTIVEREPS (line 6). The augmented feature vectors x 1 , ..., x m represent the argument's placeholder, conditioned on the text of the statute and case.…”

Section: Algorithm 1 Argument Instantiation For a Single Subsectionmentioning

confidence: 99%

See 1 more Smart Citation

Factoring Statutory Reasoning as Language Understanding Challenges

Holzenberger

Durme

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

Self Cite

View full text Add to dashboard Cite

Statutory reasoning is the task of determining whether a legal statute, stated in natural language, applies to the text description of a case. Prior work introduced a resource that approached statutory reasoning as a monolithic textual entailment problem, with neural baselines performing nearly at-chance. To address this challenge, we decompose statutory reasoning into four types of language-understanding challenge problems, through the introduction of concepts and structure found in Prolog programs. Augmenting an existing benchmark, we provide annotations for the four tasks, and baselines for three of them. Models for statutory reasoning are shown to benefit from the additional structure, improving on prior baselines. Further, the decomposition into subtasks facilitates finer-grained model diagnostics and clearer incremental progress.

show abstract

“…The ability to answer "IDK" allows one to address more realistic situations in reading comprehension, both as an end task and as an intermediary step for other NLP applications, such as QA-based event extraction (Chen et al, 2020;Lyu et al, 2021) or QA-based summarization evaluation (Deutsch et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Do We Know What We Don’t Know? Studying Unanswerable Questions beyond SQuAD 2.0

Sulem¹,

Hay²,

Roth³

2021

Findings of the Association for Computational Linguistics: EMNLP 2021

View full text Add to dashboard Cite

Understanding when a text snippet does not provide a sought after information is an essential part of natural language understanding. Recent work (SQuAD 2.0, Rajpurkar et al., 2018) has attempted to make some progress in this direction by enriching the SQuAD dataset for the Extractive QA task with unanswerable questions. However, as we show, the performance of a top system trained on SQuAD 2.0 drops considerably in out-of-domain scenarios, limiting its use in practical situations. In order to study this we build an out-of-domain corpus, focusing on simple event-based questions and distinguish between two types of IDK questions: competitive questions, where the context includes an entity of the same type as the expected answer, and simpler, noncompetitive questions where there is no entity of the same type in the context. We find that SQuAD 2.0-based models fail even in the case of the simpler questions. We then analyze the similarities and differences between the IDK phenomenon in Extractive QA and the Recognizing Textual Entailments task (RTE, Dagan et al., 2013) and investigate the extent to which the latter can be used to improve the performance. 1

show abstract

Reading the Manual: Event Extraction as Definition Comprehension

Cited by 40 publications

References 23 publications

Reinforcement Learning-Based Dialogue Guided Event Extraction to Exploit Argument Relations

Reinforcement Learning-Based Dialogue Guided Event Extraction to Exploit Argument Relations

Factoring Statutory Reasoning as Language Understanding Challenges

Do We Know What We Don’t Know? Studying Unanswerable Questions beyond SQuAD 2.0

Contact Info

Product

Resources

About