Joint Parsing and Semantic Role Labeling

By Charles Sutton, Andrew McCallum. 2005

69 citations recorded by the source corpus.

A striking feature of human syntactic processing is that it is context-dependent, that is, it seems to take into account semantic information from the discourse context and world knowledge. In this paper, we attempt to use this insight to bridge the gap between SRL results from gold parses and from automatically-generated parses. To do this, we jointly perform parsing and semantic role labeling, using a probabilistic SRL system to rerank the results of a probabilistic parser. Our current results are negative, because a locally-trained SRL model can return inaccurate probability estimates.

Subfields: Artificial Intelligence, Natural Language Processing, Information Extraction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Information Extraction

Citations in the corpus

Natural Language Processing (Almost) from Scratch (2011, methodology): “On the other hand, Sutton and McCallum (2005a) obtain results somewhat below the state-of-the-art using joint decoding for SRL and syntactic parsing.”
Concept Bottleneck Models (2020, methodology): “…the model’s prediction of y. Interventions do affect models that use c as auxiliary features by first predicting x → c and then predicting (x, c) → y (e.g., Sutton & McCallum (2005)), but we cannot intervene in isolation on a single concept because of the side channel from x→ y. Causal models.”
Linguistically-Informed Self-Attention for Semantic Role Labeling (2018, background): “Sutton and McCallum (2005) modeled syntactic parsing and SRL jointly, and Lewis et al. (2015) jointly modeled SRL and CCG parsing.”
Introduction to the CoNLL-2005 Shared Task: Semantic Role Labeling (2005, methodology): “In particular, 8 teams used the Maximum Entropy (ME) statistical framework (Che et al., 2005; Haghighi et al., 2005; Park and Rim, 2005; Tjong Kim Sang et al., 2005; Sutton and McCallum, 2005; Tsai et al., 2005; Yi and Palmer, 2005; Venkatapathy et al., 2005).”
Toward Holistic Scene Understanding: Feedback Enabled Cascaded Classification Models (2012, background): “Recently, several approaches have tried to combine these different classifiers for related tasks in vision [1], [2], [3], [4], [5], [6], [7], [8], [9], [10]; however, most of them tend to be ad hoc (i.e., a hard-coded rule is used) and often an intimate knowledge of the inner workings of the…”
A unified architecture for natural language processing: deep neural networks with multitask learning (2008, background): “In (Sutton & McCallum, 2005a) the authors showed that one could learn the tasks independently, hence using diﬀerent training sets, by only leveraging predictions jointly in a test time decoding step, and still obtain improved results.”
Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Auto-Encoders (2019, background): “, 2012), semantic role labeling (Sutton and McCallum, 2005; He et al., 2018), machine translation (Aharoni and Goldberg, 2017; Eriguchi et al.”
Forest Rescoring: Faster Decoding with Integrated Language Models (2007, unknown): “…algorithms have potential applications to other computationally intensive tasks involving combinations of different models, for example, head-lexicalized parsing (Collins, 1997); joint parsing and semantic role labeling (Sutton and McCallum, 2005); or tagging and parsing with non-local features.”
Towards Holistic Scene Understanding: Feedback Enabled Cascaded Classification Models (2010, background): “Sutton and McCallum [6] combined a parsing model with a semantic role labeling model into a unified probabilis- tic framework that solved both simultaneously.”
Better k-best Parsing (2005, methodology): “So we might want to postpone some disambiguation by propagating k-best lists to subsequent phases, as in joint parsing and semantic role labeling (Gildea and Jurafsky, 2002; Sutton and McCallum, 2005), information extraction and coreference resolution (Wellner et al.”