Semantic Role Labeling with Neural Network Factors

FitzGerald, Nicholas; Täckström, Oscar; Ganchev, Kuzman; Das, Dipanjan

doi:10.18653/v1/d15-1112

Cited by 110 publications

(110 citation statements)

References 30 publications

Supporting

Mentioning

107

Contrasting

Order By: Relevance

“…) is a graphical model with global factors ; FitzGerald (Struct. ) is an improved version of the graphical model with non-linear potential functions instead of linear ones; FitzGerald (Struct., PoE) further employs an ensemble with the product-of-experts (PoE) (Hinton, 2002);and FitzGerald (Local, PoE, Joint) indicates the best reported results in FitzGerald et al (2015) which uses local factors and additional training data from CoNLL 2005. We can see that our sequential model alone is already close to the state of the art.…”

Section: Framenet Resultsmentioning

confidence: 99%

“…Table 5 shows the results of our SRL models on the CoNLL 2005 data. Our baselines include the best feature-based systems of Surdeanu et al (2007), Toutanova et al (2008), and Punyakanok et al (2008), the recurrent neural network model (DB-LSTM) (Zhou and Xu, 2015), the graphical model with global factors and the improved versions that use neural network factors (FitzGerald et al, 2015). Note that our sequential model in this setting is essentially the same as the DB-LSTM model (Zhou and Xu, 2015) since all the frame-specific constraints are removed, except that we use simpler input features.…”

Section: Framenet Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Joint Sequential and Relational Model for Frame-Semantic Parsing

Yang¹,

Mitchell²

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

We introduce a new method for framesemantic parsing that significantly improves the prior state of the art. Our model leverages the advantages of a deep bidirectional LSTM network which predicts semantic role labels word by word and a relational network which predicts semantic roles for individual text expressions in relation to a predicate. The two networks are integrated into a single model via knowledge distillation, and a unified graphical model is employed to jointly decode frames and semantic roles during inference. Experiments on the standard FrameNet data show that our model significantly outperforms existing neural and non-neural approaches, achieving a 5.7 F1 gain over the current state of the art, for full frame structure extraction.

show abstract

Section: Framenet Resultsmentioning

confidence: 99%

Section: Framenet Resultsmentioning

confidence: 99%

A Joint Sequential and Relational Model for Frame-Semantic Parsing

Yang¹,

Mitchell²

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…Additionally, a number of systems exploit syntactic information (Roth and Lapata, 2016;. Some of the results are obtained with ensemble systems (FitzGerald et al, 2015;Roth and Lapata, 2016). As we observe, the baseline model (see Section 2) is quite strong, and outperforms the previous state-of-the-art systems on both in-domain and out-of-domain sets on English.…”

Section: Overall Resultsmentioning

confidence: 82%

Capturing Argument Interaction in Semantic Role Labeling with Capsule Networks

Chen¹,

Lyu²,

Titov³

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

Semantic role labeling (SRL) involves extracting propositions (i.e. predicates and their typed arguments) from natural language sentences. State-of-the-art SRL models rely on powerful encoders (e.g., LSTMs) and do not model non-local interaction between arguments. We propose a new approach to modeling these interactions while maintaining efficient inference. Specifically, we use Capsule Networks (Sabour et al., 2017): each proposition is encoded as a tuple of capsules, one capsule per argument type (i.e. role). These tuples serve as embeddings of entire propositions. In every network layer, the capsules interact with each other and with representations of words in the sentence. Each iteration results in updated proposition embeddings and updated predictions about the SRL structure. Our model substantially outperforms the nonrefinement baseline model on all 7 CoNLL-2019 languages and achieves state-of-the-art results on 5 languages (including English) for dependency SRL. We analyze the types of mistakes corrected by the refinement procedure. For example, each role is typically (but not always) filled with at most one argument. Whereas enforcing this approximate constraint is not useful with the modern SRL system, iterative procedure corrects the mistakes by capturing this intuition in a flexible and contextsensitive way. 1

show abstract

“…Although many studies confirmed that embeddings obtained from distributional similarity can be useful in a variety of different tasks, (Levy et al, 2015) showed that the semantic knowledge encoded by general-purpose similarity embeddings is limited, and that enforcing the learnt representations to distinguish functional similarity from relatedness is beneficial. For this purpose, many task-specific embeddings have been proposed for a variety of tasks including (Riedel et al, 2013) for binary relation extraction and (FitzGerald et al, 2015) for semantic role labeling. This work aims to preserve more far reaching structures, namely analogies between pairs of entities.…”

Section: Related Workmentioning

confidence: 99%

Learning Analogy-Preserving Sentence Embeddings for Answer Selection

Diallo¹,

Zopf²,

Fürnkranz³

2019

Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)

View full text Add to dashboard Cite

Answer selection aims at identifying the correct answer for a given question from a set of potentially correct answers. Contrary to previous works, which typically focus on the semantic similarity between a question and its answer, our hypothesis is that question-answer pairs are often in analogical relation to each other. Using analogical inference as our use case, we propose a framework and a neural network architecture for learning dedicated sentence embeddings that preserve analogical properties in the semantic space. We evaluate the proposed method on benchmark datasets for answer selection and demonstrate that our sentence embeddings indeed capture analogical properties better than conventional embeddings, and that analogy-based question answering outperforms a comparable similaritybased technique.

show abstract

Semantic Role Labeling with Neural Network Factors

Cited by 110 publications

References 30 publications

A Joint Sequential and Relational Model for Frame-Semantic Parsing

A Joint Sequential and Relational Model for Frame-Semantic Parsing

Capturing Argument Interaction in Semantic Role Labeling with Capsule Networks

Learning Analogy-Preserving Sentence Embeddings for Answer Selection

Contact Info

Product

Resources

About