We present the second shared task on eye-tracking data prediction of the Cognitive Modeling and Computational Linguistics Workshop (CMCL).
For each probing task, we identify the most relevant semantic features and we show that there is a correlation between the embedding performance and how they encode those features.
The goal of the task is to predict 5 different token- level eye-tracking metrics of the Zurich Cognitive Language Processing Corpus (ZuCo).
One containing pairs for each of the training languages (systems were evaluated in a monolingual fashion) and the other proposing a surprise language to test the crosslingual transfer capabilities of the systems.
Adverse Drug Event (ADE) extraction models can rapidly examine large collections of social media texts, detecting mentions of drug-related adverse reactions and trigger medical investigations.
This paper introduces SupCL-Seq, which extends the supervised contrastive learning from computer vision to the optimization of sequence representations in NLP.
Adverse Events (AE) are harmful events resulting from the use of medical products.
Prior research has explored the ability of computational models to predict a word semantic fit with a given predicate.
In recent years, Internet users are reporting Adverse Drug Events (ADE) on social media, blogs and health forums.
Pretrained transformer-based models, such as BERT and its variants, have become a common choice to obtain state-of-the-art performances in NLP tasks.
We evaluate the model on both deciphered languages (Gothic, Ugaritic) and an undeciphered one (Iberian).
We propose, instead, a model-agnostic framework that consists of two modules: (1) a span extractor, which identifies the crucial information connecting claim and evidence; and (2) a classifier that combines claim, evidence, and the extracted spans to predict the veracity of the claim.
While neural embeddings represent a popular choice for word representation in a wide variety of NLP tasks, their usage for thematic fit modeling has been limited, as they have been reported to lag behind syntax-based count models.
In this paper, we propose a Structured Distributional Model (SDM) that combines word embeddings with formal semantics and is based on the assumption that sentences represent events and situations.
Text attribute transfer aims to automatically rewrite sentences such that they possess certain linguistic attributes, while simultaneously preserving their semantic content.
This paper describes the SemEval 2018 Shared Task on Hypernym Discovery.
This paper describes BomJi, a supervised system for capturing discriminative attributes in word pairs (e. g. yellow as discriminative for banana over watermelon).
Ranked #3 on Relation Extraction on SemEval 2018 Task 10
Despite the number of NLP studies dedicated to thematic fit estimation, little attention has been paid to the related task of composing and updating verb argument expectations.
This paper explores the information-theoretic measure entropy to detect metaphoric change, transferring ideas from hypernym detection to research on language change.
The fundamental role of hypernymy in NLP has motivated the development of many methods for the automatic identification of this relation, most of which rely on word distribution.
Ranked #7 on Hypernym Discovery on Music domain
The task is split into two subtasks: (i) identification of related word pairs vs. unrelated ones; (ii) classification of the word pairs according to their semantic relation.
In Distributional Semantic Models (DSMs), Vector Cosine is widely used to estimate similarity between word vectors, although this measure was noticed to suffer from several shortcomings.
Several studies on sentence processing suggest that the mental lexicon keeps track of the mutual expectations between words.
In this paper, we claim that vector cosine, which is generally considered among the most efficient unsupervised measures for identifying word similarity in Vector Space Models, can be outperformed by an unsupervised measure that calculates the extent of the intersection among the most mutually dependent contexts of the target words.
In this paper, we describe ROOT13, a supervised system for the classification of hypernyms, co-hyponyms and random words.
In this paper, we claim that Vector Cosine, which is generally considered one of the most efficient unsupervised measures for identifying word similarity in Vector Space Models, can be outperformed by a completely unsupervised measure that evaluates the extent of the intersection among the most associated contexts of two target words, weighting such intersection according to the rank of the shared contexts in the dependency ranked lists.
When the classification is binary, ROOT9 achieves the following results against the baseline: hypernyms-co-hyponyms 95. 7% vs. 69. 8%, hypernyms-random 91. 8% vs. 64. 1% and co-hyponyms-random 97. 8% vs. 79. 4%.