An Unsupervised Model for Instance Level Subcategorization Acquisition

By Simon Baker, Roi Reichart, Anna Korhonen. 2014

85 citations recorded by the source corpus.

Most existing systems for subcategorization frame (SCF) acquisition rely on supervised parsing and infer SCF distributions at type, rather than instance level. These systems suffer from poor portability across domains and their benefit for NLP tasks that involve sentence-level processing is limited. We propose a new unsupervised, Markov Random Field-based model for SCF acquisition which is designed to address these problems. The system relies on supervised POS tagging rather than parsing, and is capable of learning SCFs at instance level. We perform evaluation against gold standard data which shows that our system outperforms several supervised and type-level SCF baselines. We also conduct task-based evaluation in the context of verb similarity prediction, demonstrating that a vector space model based on our SCFs substantially outperforms a lexical model and a model based on a supervised parser 1 .

Subfields: Artificial Intelligence, Natural Language Processing

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

Citations in the corpus

Using the Output Embedding to Improve Language Models (2016, methodology): “We use: Simlex999 (Hill et al., 2016), Verb-143 (Baker et al., 2014), MEN (Bruni et al., 2014), Rare-Word (Luong et al., 2013) and MTurk-771 (Halawi et al., 2012).”
Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speech (2018, positive): “We used 13 benchmarks [30] to measure word similarity, including WS-353 [31], WS-353-REL [32], WS-353-SIM , MC-30 [33], RG-65 [34], Rare-Word [35], MEN [36], MTurk-287 [37], MTurk-771 [38], YP-130 [31], SimLex-999 [39], Verb-143 [40], and SimVerb-3500 [41].”
Rethinking embedding coupling in pre-trained language models (2020, methodology): “nship and the dot product of the word embeddings. We evaluate on MEN (Bruni et al., 2014), MTurk771 (Halawi et al., 2012), Rare-Word (Luong et al., 2013), SimLex999 (Hill et al., 2015), and Verb-143 (Baker et al., 2014). As our model uses subwords, we average the token representations for words with”
SimVerb-3500: A Large-Scale Evaluation Set of Verb Similarity (2016, methodology): “In this paper we provide a remedy for this problem by presenting a more comprehensive and representative verb pair evaluation resource.”
Evaluating word embedding models: methods and experimental results (2019, unknown): “Name Pairs Year WS-353 [40] 353 2002 WS-353-SIM [41] 203 2009 WS-353-REL [41] 252 2009 MC-30 [42] 30 1991 RG-65 [43] 65 1965 Rare-Word (RW) [44] 2034 2013 MEN [45] 3000 2012 MTurk-287 [46] 287 2011 MTurk-771 [47] 771 2012 YP-130 [48] 130 2006 SimLex-999 [49] 999 2014 Verb-143 [50] 143 2014 SimVerb-3”
The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling (2020, unknown): “…Rubenstein and Goodenough (1965), Rare-Word (or rw) (Luong et al., 2013), simLex999 (Hill et al., 2015), simverb-3500 (Gerz et al., 2016), verb-143 (Baker et al., 2014) , YP-130 Yang and Powers (2006) and the relatedness-based datasets include MEN (Bruni et al., 2012), Wordsim-353-REL (Agirre et…”
The Zero Resource Speech Challenge 2021: Spoken Language Modelling (2021, unknown): “We used a set of 13 existing semantic similarity and relatedness tests: WordSim-353 [10], WordSim-353-SIM [11], mc-30 [12], rg-65 [13], Rare-Word (or rw) [14], simLex999 [15], simverb-3500 [16], verb-143 [17] , YP-130 [10] and the relatedness-based”
SemEval-2017 Task 2: Multilingual and Cross-lingual Semantic Word Similarity (2017, background): “Given that multiple large and high-quality verb similarity datasets have been created in recent years (Yang and Powers, 2006; Baker et al., 2014; Gerz et al., 2016), we decided to focus on nominal words.”
Problems With Evaluation of Word Embeddings Using Word Similarity Tasks (2016, unknown): “(2013) Verb 144 Baker et al. (2014) SimLex 999 Hill et al.”
Learning Word Embeddings from Speech (2017, unknown): “…RG-65 [Rubenstein and Goodenough, 1965], Rare-Word [Luong et al., 2013], MEN [Bruni et al., 2012], MTurk-287 [Radinsky et al., 2011], MTurk-771 [Halawi et al., 2012], YP-130 [Yang and Powers, 2006], SimLex-999 [Hill et al., 2015], Verb-143 [Baker et al., 2014], and SimVerb-3500 [Gerz et al., 2016].”