Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userPredicate Representations and Polysemy in VerbNet Semantic Parsing
تمثيلات المسند و Polysemy في تحليل Verbnet الدلالي
337
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
على الرغم من التطورات الحديثة في الدور الدوالي الذي يدفعه ترميز النص المدرب مسبقا مثل بيرت، فإن الأداء يتخلف عند تطبيقه على المسندات لاحظ بشكل غير منتظم أثناء التدريب أو إلى الجمل في مجالات جديدة. في هذا العمل، يمكننا التحقيق في كيفية تحسين أداء وضع العلامات على الدوران المنخفض التردد والبيانات خارج نطاق البيانات باستخدام Verbnet، معجم فعل يضم الأفعال إلى فئات هرمية تستند إلى سلوك النحوية والدلية المشتركة وتحدد التمثيل الدلالي وصف العلاقات بين الحجج. نجد أن فئات Verbnet توفر مستوى فعال من التجريد، وتحسين التعميم على المساكن المنخفض التردد من خلال السماح لهم بالتعلم من الأمثلة التدريبية للندوات الأخرى المنتمدة إلى نفس الفصل. نجد أيضا أن التدريب المشترك لعلامات الدور الحرفية والأزهار المسند للفئات الحرفية للأفعال البسيطة يؤدي إلى تحسينات في كلا المهام، مما يدعم بشكل طبيعي استخراج التمثيلات الدلالية في فيربيت.
Despite recent advances in semantic role labeling propelled by pre-trained text encoders like BERT, performance lags behind when applied to predicates observed infrequently during training or to sentences in new domains. In this work, we investigate how role labeling performance on low-frequency predicates and out-of-domain data can be further improved by using VerbNet, a verb lexicon that groups verbs into hierarchical classes based on shared syntactic and semantic behavior and defines semantic representations describing relations between arguments. We find that VerbNet classes provide an effective level of abstraction, improving generalization on low-frequency predicates by allowing them to learn from the training examples of other predicates belonging to the same class. We also find that joint training of VerbNet role labeling and predicate disambiguation of VerbNet classes for polysemous verbs leads to improvements in both tasks, naturally supporting the extraction of VerbNet's semantic representations.
References used
https://aclanthology.org/
rate research
Read More
Tracking entity states is a natural language processing task assumed to require human annotation. In order to reduce the time and expenses associated with annotation, we introduce a new method to automatically extract entity states, including locatio
n and existence state of entities, following Dalvi et al. (2018) and Tandon et al. (2020). For this purpose, we rely primarily on the semantic representations generated by the state of the art VerbNet parser (Gung, 2020), and extract the entities (event participants) and their states, based on the semantic predicates of the generated VerbNet semantic representation, which is in propositional logic format. For evaluation, we used ProPara (Dalvi et al., 2018), a reading comprehension dataset which is annotated with entity states in each sentence, and tracks those states in paragraphs of natural human-authored procedural texts. Given the presented limitations of the method, the peculiarities of the ProPara dataset annotations, and that our system, Lexis, makes no use of task-specific training data and relies solely on VerbNet, the results are promising, showcasing the value of lexical resources.
Frame-semantic parsers traditionally predict predicates, frames, and semantic roles in a fixed order. This paper explores the chicken-or-egg' problem of interdependencies between these components theoretically and practically. We introduce a flexible
BERT-based sequence labeling architecture that allows for predicting frames and roles independently from each other or combining them in several ways. Our results show that our setups can approximate more complex traditional models' performance, while allowing for a clearer view of the interdependencies between the pipeline's components, and of how frame and role prediction models make different use of BERT's layers.
Accurate recovery of predicate-argument structure from a Universal Dependency (UD) parse is central to downstream tasks such as extraction of semantic roles or event representations. This study introduces compchains, a categorization of the hierarchy
of predicate dependency relations present within a UD parse. Accuracy of compchain classification serves as a proxy for measuring accurate recovery of predicate-argument structure from sentences with embedding. We analyzed the distribution of compchains in three UD English treebanks, EWT, GUM and LinES, revealing that these treebanks are sparse with respect to sentences with predicate-argument structure that includes predicate-argument embedding. We evaluated the CoNLL 2018 Shared Task UDPipe (v1.2) baseline (dependency parsing) models as compchain classifiers for the EWT, GUMS and LinES UD treebanks. Our results indicate that these three baseline models exhibit poorer performance on sentences with predicate-argument structure with more than one level of embedding; we used compchains to characterize the errors made by these parsers and present examples of erroneous parses produced by the parser that were identified using compchains. We also analyzed the distribution of compchains in 58 non-English UD treebanks and then used compchains to evaluate the CoNLL'18 Shared Task baseline model for each of these treebanks. Our analysis shows that performance with respect to compchain classification is only weakly correlated with the official evaluation metrics (LAS, MLAS and BLEX). We identify gaps in the distribution of compchains in several of the UD treebanks, thus providing a roadmap for how these treebanks may be supplemented. We conclude by discussing how compchains provide a new perspective on the sparsity of training data for UD parsers, as well as the accuracy of the resulting UD parses.
One of the central aspects of contextualised language models is that they should be able to distinguish the meaning of lexically ambiguous words by their contexts. In this paper we investigate the extent to which the contextualised embeddings of word
forms that display multiplicity of sense reflect traditional distinctions of polysemy and homonymy. To this end, we introduce an extended, human-annotated dataset of graded word sense similarity and co-predication acceptability, and evaluate how well the similarity of embeddings predicts similarity in meaning. Both types of human judgements indicate that the similarity of polysemic interpretations falls in a continuum between identity of meaning and homonymy. However, we also observe significant differences within the similarity ratings of polysemes, forming consistent patterns for different types of polysemic sense alternation. Our dataset thus appears to capture a substantial part of the complexity of lexical ambiguity, and can provide a realistic test bed for contextualised embeddings. Among the tested models, BERT Large shows the strongest correlation with the collected word sense similarity ratings, but struggles to consistently replicate the observed similarity patterns. When clustering ambiguous word forms based on their embeddings, the model displays high confidence in discerning homonyms and some types of polysemic alternations, but consistently fails for others.
Deciding whether a semantically ambiguous word is homonymous or polysemous is equivalent to establishing whether it has any pair of senses that are semantically unrelated. We present novel methods for this task that leverage information from multilin
gual lexical resources. We formally prove the theoretical properties that provide the foundation for our methods. In particular, we show how the One Homonym Per Translation hypothesis of Hauer and Kondrak (2020a) follows from the synset properties formulated by Hauer and Kondrak (2020b). Experimental evaluation shows that our approach sets a new state of the art for homonymy detection.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
