Search Results for author:
Found 31 papers, 7 papers with code
Looking for a Role for Word Embeddings in Eye-Tracking Features Prediction: Does Semantic Similarity Help?
Eye-tracking psycholinguistic studies have suggested that context-word semantic coherence and predictability influence language processing during the reading activity.
From Speed to Car and Back: An Exploratory Study about Associations between Abstract Nouns and Images
Abstract concepts, notwithstanding their lack of physical referents in real world, are grounded in sensorimotor experience.
A Comparison between Named Entity Recognition Models in the Biomedical Domain
The domain-specialised application of Named Entity Recognition (NER) is known as Biomedical NER (BioNER), which aims to identify and classify biomedical concepts that are of interest to researchers, such as genes, proteins, chemical compounds, drugs, mutations, diseases, and so on.
Decoding Word Embeddings with Brain-Based Semantic Features
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.
PIHKers at CMCL 2021 Shared Task: Cosine Similarity and Surprisal to Predict Human Reading Patterns.
Eye-tracking psycholinguistic studies have revealed that context-word semantic coherence and predictability influence language processing.
A howling success or a working sea? Testing what BERT knows about metaphors
Metaphor is a widespread linguistic and cognitive phenomenon that is ruled by mechanisms which have received attention in the literature.
Pragmatic and Logical Inferences in NLI Systems: The Case of Conjunction Buttressing
An intelligent system is expected to perform reasonable inferences, accounting for both the literal meaning of a word and the meanings a word can acquire in different contexts.
Does BERT Recognize an Agent? Modeling Dowty’s Proto-Roles with Contextual Embeddings
Contextual embeddings build multidimensional representations of word tokens based on their context of occurrence.
Comparing Plausibility Estimates in Base and Instruction-Tuned Large Language Models
Experiment 1 shows that, across model architectures and plausibility datasets, (i) log likelihood ($\textit{LL}$) scores are the most reliable indicator of sentence plausibility, with zero-shot prompting yielding inconsistent and typically poor results; (ii) $\textit{LL}$-based performance is still inferior to human performance; (iii) instruction-tuned models have worse $\textit{LL}$-based performance than base models.
Agentività e telicità in GilBERTo: implicazioni cognitive
The goal of this study is to investigate whether a Transformer-based neural language model infers lexical semantics and use this information for the completion of morphosyntactic patterns.
Understanding Natural Language Understanding Systems. A Critical Analysis
I contend that they incorporate important aspects of the way language is learnt and processed by humans, but at the same time they lack key interpretive and inferential skills that it is unlikely they can attain unless they are integrated with structured knowledge and the ability to exploit it for language use.
Event knowledge in large language models: the gap between the impossible and the unlikely
Overall, our results show that important aspects of event knowledge naturally emerge from distributional linguistic patterns, but also highlight a gap between representations of possible/impossible and likely/unlikely events.
Word Order Matters when you Increase Masking
We find that the necessity of position information increases with the amount of masking, and that masked language models without position encodings are not able to reconstruct this information on the task.
Subject Verb Agreement Error Patterns in Meaningless Sentences: Humans vs. BERT
We compare the performance of BERT-base to that of humans, obtained with a psycholinguistic online crowdsourcing experiment.
Probing for the Usage of Grammatical Number
We also find that BERT uses a separate encoding of grammatical number for nouns and verbs.
Does BERT really agree ? Fine-grained Analysis of Lexical Dependence on a Syntactic Task
Although transformer-based Neural Language Models demonstrate impressive performance on a variety of tasks, their generalization abilities are not well understood.
Did the Cat Drink the Coffee? Challenging Transformers with Generalized Event Knowledge
Prior research has explored the ability of computational models to predict a word semantic fit with a given predicate.
A comparative evaluation and analysis of three generations of Distributional Semantic Models
In this paper, we perform a comprehensive evaluation of type distributional vectors, either produced by static DSMs or obtained by averaging the contextualized vectors generated by BERT.
Comparing Probabilistic, Distributional and Transformer-Based Models on Logical Metonymy Interpretation
In linguistics and cognitive science, Logical metonymies are defined as type clashes between an event-selecting verb and an entity-denoting noun (e. g.
Don't Invite BERT to Drink a Bottle: Modeling the Interpretation of Metonymies Using BERT and Distributional Representations
The results reveal that, while BERT ability to deal with metonymy is quite limited, SDM is good at predicting the meaning of metonymic expressions, providing support for an account of metonymy based on event knowledge.
PISA: A measure of Preference In Selection of Arguments to model verb argument recoverability
Our paper offers a computational model of the semantic recoverability of verb arguments, tested in particular on direct objects and Instruments.
A Structured Distributional Model of Sentence Meaning and Processing
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.
Is Structure Necessary for Modeling Argument Expectations in Distributional Semantics?
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.
Measuring Thematic Fit with Distributional Feature Overlap
In this paper, we introduce a new distributional method for modeling predicate-argument thematic fit judgments.
The Effects of Data Size and Frequency Range on Distributional Semantic Models
This paper investigates the effects of data size and frequency range on distributional semantic models.
Testing APSyn against Vector Cosine on Similarity Estimation
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.
Representing Verbs with Rich Contexts: an Evaluation on Verb Similarity
Several studies on sentence processing suggest that the mental lexicon keeps track of the mutual expectations between words.
Unsupervised Measure of Word Similarity: How to Outperform Co-occurrence and Vector Cosine in VSMs
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.
Nine Features in a Random Forest to Learn Taxonomical Semantic Relations
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%.
What a Nerd! Beating Students and Vector Cosine in the ESL and TOEFL Datasets
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.
ROOT13: Spotting Hypernyms, Co-Hyponyms and Randoms
In this paper, we describe ROOT13, a supervised system for the classification of hypernyms, co-hyponyms and random words.
