Word embeddings are trained to predict word cooccurrence statistics, which leads them to possess different lexical properties (syntactic, semantic, etc.) depending on the notion of context defined at training time. These properties manifest when querying the embedding space for the most similar vectors, and when used at the input layer of deep neural networks trained to solve downstream NLP problems. Meta-embeddings combine multiple sets of differently trained word embeddings, and have been shown to successfully improve intrinsic and extrinsic performance over equivalent models which use just one set of source embeddings. We introduce word prisms: a simple and efficient meta-embedding method that learns to combine source embeddings according to the task at hand. Word prisms learn orthogonal transformations to linearly combine the input source embeddings, which allows them to be very efficient at inference time. We evaluate word prisms in comparison to other meta-embedding methods on six extrinsic evaluations and observe that word prisms offer improvements in performance on all tasks.
Jingyi He, Kc Tsiolis, Kian Kenyon-Dean, and Jackie Chi Kit Cheung. 2020.Learning Efficient Task-Specific Meta-Embeddings with Word Prisms. InProceedings of the 28th International Conference on Computational Linguistics, pages 1229–1241, Barcelona, Spain (Online). International Committee on Computational Linguistics.
@inproceedings{he-etal-2020-learning, title = "Learning Efficient Task-Specific Meta-Embeddings with Word Prisms", author = "He, Jingyi and Tsiolis, Kc and Kenyon-Dean, Kian and Cheung, Jackie Chi Kit", editor = "Scott, Donia and Bel, Nuria and Zong, Chengqing", booktitle = "Proceedings of the 28th International Conference on Computational Linguistics", month = dec, year = "2020", address = "Barcelona, Spain (Online)", publisher = "International Committee on Computational Linguistics", url = "https://aclanthology.org/2020.coling-main.106/", doi = "10.18653/v1/2020.coling-main.106", pages = "1229--1241", abstract = "Word embeddings are trained to predict word cooccurrence statistics, which leads them to possess different lexical properties (syntactic, semantic, etc.) depending on the notion of context defined at training time. These properties manifest when querying the embedding space for the most similar vectors, and when used at the input layer of deep neural networks trained to solve downstream NLP problems. Meta-embeddings combine multiple sets of differently trained word embeddings, and have been shown to successfully improve intrinsic and extrinsic performance over equivalent models which use just one set of source embeddings. We introduce word prisms: a simple and efficient meta-embedding method that learns to combine source embeddings according to the task at hand. Word prisms learn orthogonal transformations to linearly combine the input source embeddings, which allows them to be very efficient at inference time. We evaluate word prisms in comparison to other meta-embedding methods on six extrinsic evaluations and observe that word prisms offer improvements in performance on all tasks."}
<?xml version="1.0" encoding="UTF-8"?><modsCollection xmlns="http://www.loc.gov/mods/v3"><mods ID="he-etal-2020-learning"> <titleInfo> <title>Learning Efficient Task-Specific Meta-Embeddings with Word Prisms</title> </titleInfo> <name type="personal"> <namePart type="given">Jingyi</namePart> <namePart type="family">He</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Kc</namePart> <namePart type="family">Tsiolis</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Kian</namePart> <namePart type="family">Kenyon-Dean</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Jackie</namePart> <namePart type="given">Chi</namePart> <namePart type="given">Kit</namePart> <namePart type="family">Cheung</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <originInfo> <dateIssued>2020-12</dateIssued> </originInfo> <typeOfResource>text</typeOfResource> <relatedItem type="host"> <titleInfo> <title>Proceedings of the 28th International Conference on Computational Linguistics</title> </titleInfo> <name type="personal"> <namePart type="given">Donia</namePart> <namePart type="family">Scott</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Nuria</namePart> <namePart type="family">Bel</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Chengqing</namePart> <namePart type="family">Zong</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <originInfo> <publisher>International Committee on Computational Linguistics</publisher> <place> <placeTerm type="text">Barcelona, Spain (Online)</placeTerm> </place> </originInfo> <genre authority="marcgt">conference publication</genre> </relatedItem> <abstract>Word embeddings are trained to predict word cooccurrence statistics, which leads them to possess different lexical properties (syntactic, semantic, etc.) depending on the notion of context defined at training time. These properties manifest when querying the embedding space for the most similar vectors, and when used at the input layer of deep neural networks trained to solve downstream NLP problems. Meta-embeddings combine multiple sets of differently trained word embeddings, and have been shown to successfully improve intrinsic and extrinsic performance over equivalent models which use just one set of source embeddings. We introduce word prisms: a simple and efficient meta-embedding method that learns to combine source embeddings according to the task at hand. Word prisms learn orthogonal transformations to linearly combine the input source embeddings, which allows them to be very efficient at inference time. We evaluate word prisms in comparison to other meta-embedding methods on six extrinsic evaluations and observe that word prisms offer improvements in performance on all tasks.</abstract> <identifier type="citekey">he-etal-2020-learning</identifier> <identifier type="doi">10.18653/v1/2020.coling-main.106</identifier> <location> <url>https://aclanthology.org/2020.coling-main.106/</url> </location> <part> <date>2020-12</date> <extent unit="page"> <start>1229</start> <end>1241</end> </extent> </part></mods></modsCollection>
%0 Conference Proceedings%T Learning Efficient Task-Specific Meta-Embeddings with Word Prisms%A He, Jingyi%A Tsiolis, Kc%A Kenyon-Dean, Kian%A Cheung, Jackie Chi Kit%Y Scott, Donia%Y Bel, Nuria%Y Zong, Chengqing%S Proceedings of the 28th International Conference on Computational Linguistics%D 2020%8 December%I International Committee on Computational Linguistics%C Barcelona, Spain (Online)%F he-etal-2020-learning%X Word embeddings are trained to predict word cooccurrence statistics, which leads them to possess different lexical properties (syntactic, semantic, etc.) depending on the notion of context defined at training time. These properties manifest when querying the embedding space for the most similar vectors, and when used at the input layer of deep neural networks trained to solve downstream NLP problems. Meta-embeddings combine multiple sets of differently trained word embeddings, and have been shown to successfully improve intrinsic and extrinsic performance over equivalent models which use just one set of source embeddings. We introduce word prisms: a simple and efficient meta-embedding method that learns to combine source embeddings according to the task at hand. Word prisms learn orthogonal transformations to linearly combine the input source embeddings, which allows them to be very efficient at inference time. We evaluate word prisms in comparison to other meta-embedding methods on six extrinsic evaluations and observe that word prisms offer improvements in performance on all tasks.%R 10.18653/v1/2020.coling-main.106%U https://aclanthology.org/2020.coling-main.106/%U https://doi.org/10.18653/v1/2020.coling-main.106%P 1229-1241
Jingyi He, Kc Tsiolis, Kian Kenyon-Dean, and Jackie Chi Kit Cheung. 2020.Learning Efficient Task-Specific Meta-Embeddings with Word Prisms. InProceedings of the 28th International Conference on Computational Linguistics, pages 1229–1241, Barcelona, Spain (Online). International Committee on Computational Linguistics.