Large-scale learning of word relatedness with constraints

By Guy Halawi, Gideon Dror, Evgeniy Gabrilovich, Yehuda Koren. 2012

275 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing, Representation & Self-Supervised Learning

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 Representation & Self-Supervised Learning

Citations in the corpus

Learning Gender-Neutral Word Embeddings (2018, neutral): “Embeddings are tested on multiple datasets: WS353-ALL (Finkel-stein et al., 2001), RG-65 (Rubenstein and Goode-nough, 1965), MTurk-287 (Radinsky et al., 2011), MTurk-771 (Halawi et al., 2012), RW (Luong et al., 2013), and MEN-TR-3k (Bruni et al., datasets.”
ConceptNet 5.5: An Open Multilingual Graph of General Knowledge (2016, methodology): “Its high scores on both the Rare Words dataset and the crowd-sourced MEN-3000 and MTurk-771 datasets, exceeding the performance of other embeddings with high conﬁdence, shows both the breadth and the depth of its understanding of words.”
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].”
Don’t count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors (2014, methodology): “The current state of the art is reached by Halawi et al. (2012) with a method that is in the spirit of the predict models, but lets synonymy information from WordNet constrain the learning process (by favoring solutions in which WordNet syn-onyms are near in semantic space).”
Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection (2020, methodology): “We use the following datasets: SimLex999 (Hill et al., 2015), Word-Sim353 (Agirre et al., 2009) which contain two evaluations, on words similarity and relatedness and ﬁnally on Mturk-771 (Halawi et al., 2012).”
Rethinking embedding coupling in pre-trained language models (2020, neutral): “, 2014), MTurk771 (Halawi et al., 2012), Rare-Word (Luong et al.”
Probabilistic FastText for Multi-Sense Word Embeddings (2018, unknown): “…SL-999 (Hill et al., 2014), WS-353 (Finkelstein et al., 2002), MEN-3k (Bruni et al., 2014), MC-30 (Miller and Charles, 1991), RG-65 (Rubenstein and Goode-nough, 1965), YP-130 (Yang and Powers, 2006), MTurk(-287,-771) (Radinsky et al., 2011; Halawi et al., 2012), and RW-2k (Luong et al., 2013).”
Turkers, Scholars, "Arafat" and "Peace": Cultural Communities and Algorithmic Gold Standards (2015, methodology): “Validation assessments: We added four validation assessments following the procedure of [18].”
Gender-preserving Debiasing for Pre-trained Word Embeddings (2019, unknown): “…datasets: Word Similarity 353 dataset ( WS ) (Finkelstein et al., 2001), Rubenstein-Goodenough dataset ( RG ) (Rubenstein and Good-enough, 1965), MTurk (Halawi et al., 2012), rare words dataset ( RW ) (Luong et al., 2013), MEN dataset (Bruni et al., 2012) and SimLex dataset (Hill et al., 2015).”
Metrology for AI: From Benchmarks to Instruments (2019, methodology): “(Halawi et al. 2012) proposes a large-scale data mining approach to learning word-word relatedness, called CLEAR.”
Evaluating word embedding models: methods and experimental results (2019, unknown): “Rare-Word (RW) [47] 2034 2013 MEN [48] 3000 2012 MTurk-287 [49] 287 2011 MTurk-771 [50] 771 2012 YP-130 [51] 130 2006 SimLex-999 [52] 999 2014 Verb-143 [53] 143 2014 SimVerb-3500 [54] 3500 2016”
Align, Disambiguate and Walk: A Unified Approach for Measuring Semantic Similarity (2013, unknown): “…levels: methods for word similarity are rarely applied to documents or even single sentences (Budanitsky and Hirst, 2006; Radin-sky et al., 2011; Halawi et al., 2012), while document-based similarity methods require more linguistic features, which often makes them in-applicable at the word or…”
The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling (2020, unknown): “…(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 al., 2009), mturk-287 (Radinsky et al., 2011), mturk-771 (Halawi et al., 2012).”
Community Evaluation and Exchange of Word Vectors at wordvectors.org (2014, background): “Similar in spirit is the MTruk-771 6 (Halawi et al., 2012) dataset that contains 771 word pairs whose similarity was crowdsourced from AMT.”
A Causal Inference Method for Reducing Gender Bias in Word Embedding Relations (2019, unknown): “2011), MTurk-771 (Halawi et al. 2012), SimLex-999 (Hill, Reichart, and Korhonen 2015), and SimVerb-3500 (Gerz et al.”