Search Results for author: Murathan Kurfali

Found 15 papers, 5 papers with code

TRAVIS at PARSEME Shared Task 2020: How good is (m)BERT at seeing the unseen?

1 code implementation COLING (MWE) 2020 Murathan Kurfali

This paper describes the TRAVIS system built for the PARSEME Shared Task 2020 on semi-supervised identification of verbal multiword expressions.

Disambiguation of Potentially Idiomatic Expressions with Contextual Embeddings

no code implementations COLING (MWE) 2020 Murathan Kurfali, Robert Östling

The unsupervised classification, similarly, yields very impressive results, comparing favorably to the supervised classifier for the majority of the expressions.

Let’s be explicit about that: Distant supervision for implicit discourse relation classification via connective prediction

no code implementations ACL (unimplicit) 2021 Murathan Kurfali, Robert Östling

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

A Sentiment-annotated Dataset of English Causal Connectives

1 code implementation COLING (LAW) 2020 Marta Andersson, Murathan Kurfali, Robert Östling

This paper investigates the semantic prosody of three causal connectives: due to, owing to and because of in seven varieties of the English language.

Language Modelling

Zero-shot cross-lingual identification of direct speech using distant supervision

no code implementations COLING (LaTeCHCLfL, CLFL, LaTeCH) 2020 Murathan Kurfali, Mats Wirén

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

no code implementations EMNLP (CODI) 2020 Murathan Kurfali, Sibel Ozer, Deniz Zeyrek, Amália Mendes

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.

Relation

Evaluation of really good grammatical error correction

1 code implementation17 Aug 2023 Robert Östling, Katarina Gillholm, Murathan Kurfali, Marie Mattson, Mats Wirén

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.

Grammatical Error Detection

Language Embeddings Sometimes Contain Typological Generalizations

1 code implementation19 Jan 2023 Robert Östling, Murathan Kurfali

To what extent can neural network models learn generalizations about language structure, and how do we find out what they have learned?

Multilingual Word Embeddings

Probing Multilingual Language Models for Discourse

no code implementations ACL (RepL4NLP) 2021 Murathan Kurfali, Robert Östling

Pre-trained multilingual language models have become an important building block in multilingual natural language processing.

Cross-Lingual Transfer Sentence

Let's be explicit about that: Distant supervision for implicit discourse relation classification via connective prediction

no code implementations6 Jun 2021 Murathan Kurfali, Robert Östling

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

Labeling Explicit Discourse Relations using Pre-trained Language Models

no code implementations21 Jun 2020 Murathan Kurfali

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.

Discourse Parsing

Zero-shot transfer for implicit discourse relation classification

1 code implementation30 Jul 2019 Murathan Kurfali, Robert Östling

Automatically classifying the relation between sentences in a discourse is a challenging task, in particular when there is no overt expression of the relation.

Classification General Classification +3

A Trie-Structured Bayesian Model for Unsupervised Morphological Segmentation

no code implementations24 Apr 2017 Murathan Kurfali, Ahmet Üstün, Burcu Can

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.

Segmentation Word Embeddings

Turkish PoS Tagging by Reducing Sparsity with Morpheme Tags in Small Datasets

no code implementations9 Mar 2017 Burcu Can, Ahmet Üstün, Murathan Kurfali

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.

Part-Of-Speech Tagging POS +1

Cannot find the paper you are looking for? You can Submit a new open access paper.