| Challenge: | Existing methods for relation classification are based on word embeddings, but they pose a greater challenge than syntactic and semantic relations. |
| Approach: | They propose a distributional landscape based on word embeddings as a suitable basis for relation classification of collocations . they also conduct experiments on a subset of this benchmark . |
| Outcome: | The proposed dataset is compared to the well known DiffVec dataset and shows that it is more efficient than the standard methods. |
Similar Papers
Evaluating language models for the retrieval and categorization of lexical collocations (2021.eacl-main)
Copied to clipboard
| Challenge: | Lexical collocations are idiosyncratic combinations of two syntactically bound lexical items. |
| Approach: | They perform an exhaustive analysis of current language models for collocation understanding . they first construct a dataset of apparitions of lexical collocations in context . |
| Outcome: | The proposed models perform well in distinguishing light verb constructions, especially if the collocation’s first argument acts as subject, but often fail to distinguish, first, different syntactic structures within the same semantic category, and second, fine-grained semantic categories which restrict the use of small sets of valid collocates for a given base. |
Lexical Relation Mining in Neural Word Embeddings (2020.coling-main)
Copied to clipboard
| Challenge: | Conventionally, lexical relations in word vector space have been defined by collections of relatively consistent relationships, or vector offsets, between word-pairs. |
| Approach: | They propose to use Word2Vec space of word-pairs to find lexical relations . they also demonstrate a method for approximating the presence of syntactic and semantic relations based on word vectors extracted from word embeddings. |
| Outcome: | The proposed method outperforms other validated methods in the presence of noisy offsets. |
Learning Lexical Subspaces in a Distributional Vector Space (2020.tacl-1)
Copied to clipboard
| Challenge: | Existing word embeddings that can cluster distributionally related words are weak, but they can be used to cluster words that might not be semantically similar. |
| Approach: | They propose a framework that injects lexical-semantic relations into distributional word embeddings by defining subspaces of the distributional vector space in which a lexically related relation should hold. |
| Outcome: | The proposed framework outperforms existing systems on relatedness and hypernymy tasks while being competitive on word similarity tasks. |
Collocations in Russian Lexicography and Russian Collocations Database (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing methods for collocation extraction cannot be considered perfect, argues a new study. |
| Approach: | They propose to build a database that will include dictionary and statistical collocations in Russian . the database will be based on dictionaries and online systems that describe collocation . |
| Outcome: | The proposed database will include dictionary and statistical collocations in Russian . the results can be useful for machine learning and for other NLP tasks . |
SphereRE: Distinguishing Lexical Relations with Hyperspherical Relation Embeddings (P19-1)
Copied to clipboard
| Challenge: | Lexical relations are relations between terms in lexicons. |
| Approach: | They propose a neural representation learning model to distinguish lexical relations among term pairs based on hyperspherical relation embeddings. |
| Outcome: | The proposed model outperforms state-of-the-art models on several benchmarks. |
SeVeN: Augmenting Word Embeddings with Unsupervised Relation Vectors (C18-1)
Copied to clipboard
| Challenge: | Word embeddings use fixed-dimensional vectors to represent the meaning of words. |
| Approach: | They propose a pipeline for learning relation vectors based on word vector averaging and an ad hoc autoencoder. |
| Outcome: | The proposed pipeline can capture aspects of word meaning complementary to word embeddings. |
PairRE: Knowledge Graph Embeddings via Paired Relation Vectors (2021.acl-long)
Copied to clipboard
| Challenge: | Existing knowledge graph embedding methods fail to solve two major problems at the same time, leading to unsatisfactory results. |
| Approach: | They propose a model with paired vectors for each relation representation that can be adaptively adjusted to fit for different complex relations. |
| Outcome: | Experiments on two knowledge graph datasets show the proposed model can handle complex relations and encode relation patterns. |
Semantic Specialization of Distributional Word Vectors (D19-2)
Copied to clipboard
| Challenge: | Distributional word vectors conflate various paradigmatic and syntagmatic lexico-semantic relations. |
| Approach: | This tutorial provides an overview of specialization methods for distributional word vectors . a common solution is to include external lexico-semantic knowledge in a reshaped vector space . |
| Outcome: | This paper provides an overview of specialization methods for distributional word vectors . the most recent developments include a new method for asymmetric relations in Euclidean . |
Global Relation Embedding for Relation Extraction (N18-1)
Copied to clipboard
| Challenge: | Existing methods to extract textual relations with distant supervision are limited by their reliance on supervised training data. |
| Approach: | They propose to embed relations with global statistics of relations to combat the wrong labeling problem of distant supervision. |
| Outcome: | The proposed method is more robust to training noise introduced by distant supervision and improves relation extraction models. |
Within-Between Lexical Relation Classification (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for recognizing lexical-semantic relations between words are path-based and distributional. |
| Approach: | They propose a novel Within-Between Relation model for recognizing lexical-semantic relations between words. |
| Outcome: | The proposed model outperforms baselines across various benchmarks and is competitive and competitive. |