Search Results for author:
Found 15 papers, 5 papers with code
Turkish PoS Tagging by Reducing Sparsity with Morpheme Tags in Small Datasets
We learn inflectional and derivational morpheme tags in Turkish by using conditional random fields (CRF) and we employ the morpheme tags in part-of-speech (PoS) tagging by using hidden Markov models (HMMs) to mitigate sparsity.
A Trie-Structured Bayesian Model for Unsupervised Morphological Segmentation
Our results show that using different information sources such as neural word embeddings and letter successor variety as prior information improves morphological segmentation in a Bayesian model.
Zero-shot transfer for implicit discourse relation classification
Automatically classifying the relation between sentences in a discourse is a challenging task, in particular when there is no overt expression of the relation.
Labeling Explicit Discourse Relations using Pre-trained Language Models
Labeling explicit discourse relations is one of the most challenging sub-tasks of the shallow discourse parsing where the goal is to identify the discourse connectives and the boundaries of their arguments.
Let's be explicit about that: Distant supervision for implicit discourse relation classification via connective prediction
We sidestep the lack of data through explicitation of implicit relations to reduce the task to two sub-problems: language modeling and explicit discourse relation classification, a much easier problem.
Classification
Implicit Discourse Relation Classification
+4
Probing Multilingual Language Models for Discourse
Pre-trained multilingual language models have become an important building block in multilingual natural language processing.
Language Embeddings Sometimes Contain Typological Generalizations
To what extent can neural network models learn generalizations about language structure, and how do we find out what they have learned?
Evaluation of really good grammatical error correction
We find that GPT-3 in a few-shot setting by far outperforms previous grammatical error correction systems for Swedish, a language comprising only 0. 11% of its training data.
Lightweight Connective Detection Using Gradient Boosting
In this work, we introduce a lightweight discourse connective detection system.
TRAVIS at PARSEME Shared Task 2020: How good is (m)BERT at seeing the unseen?
This paper describes the TRAVIS system built for the PARSEME Shared Task 2020 on semi-supervised identification of verbal multiword expressions.
A Sentiment-annotated Dataset of English Causal Connectives
This paper investigates the semantic prosody of three causal connectives: due to, owing to and because of in seven varieties of the English language.
Disambiguation of Potentially Idiomatic Expressions with Contextual Embeddings
The unsupervised classification, similarly, yields very impressive results, comparing favorably to the supervised classifier for the majority of the expressions.
Zero-shot cross-lingual identification of direct speech using distant supervision
Crucially, by training the classifier with the quotation marks removed, it was forced to learn the linguistic characteristics of direct speech rather than the typography of quotation marks.
TED-MDB Lexicons: Tr-EnConnLex, Pt-EnConnLex
In this work, we present two new bilingual discourse connective lexicons, namely, for Turkish-English and European Portuguese-English created automatically using the existing discourse relation-aligned TED-MDB corpus.
Let’s be explicit about that: Distant supervision for implicit discourse relation classification via connective prediction
We sidestep the lack of data through explicitation of implicit relations to reduce the task to two sub-problems: language modeling and explicit discourse relation classification, a much easier problem.
Classification
Implicit Discourse Relation Classification
+4
