PART-OF-SPEECH

VnCoreNLP: A Vietnamese Natural Language Processing Toolkit (N18-5)

Challenge:	The performance of Stanza on historical data is evaluated to assess its potential use for automated annotation.
Approach:	They evaluate the performance of a part-of-speech (POS) tagger developed for modern Polish on historical texts to assess its potential use for automated annotation.
Outcome:	The proposed POS tagger performs well on historical Polish data and pinpoints some common features of misclassified tokens.

Copied to clipboard

Thanh Vu, Dat Quoc Nguyen, Dai Quoc Nguyen, Mark Dras, Mark Johnson

Challenge:	Using word segmenters and POS taggers, Vietnamese NLP pipelines are no longer considered SOTA models for Vietnamese.
Approach:	They propose a Java NLP annotation pipeline for Vietnamese that provides rich linguistic annotations.
Outcome:	The proposed toolkit provides rich linguistic annotations to facilitate research work on Vietnamese NLP.

Neural Architectures for Fine-Grained Propaganda Detection in News (D19-50)

Copied to clipboard

Pankaj Gupta, Khushbu Saxena, Usama Yaseen, Thomas Runkler, Hinrich Schütze

DadmaTools: Natural Language Processing Toolkit for Persian Language (2022.naacl-demo)

Challenge:	MIC-CIS is a fine grained propaganda detection system . previous work focused on document level, labeling articles as propaganda .
Approach:	They propose to use different neural architectures to jointly perform propaganda detection tasks . they also investigate different ensemble schemes such as majority-voting, relax-vote, etc.
Outcome:	The proposed system performs sentences and fragment level propaganda detection tasks.

Copied to clipboard

Romina Etezadi, Mohammad Karrabi, Najmeh Zare, Mohamad Bagher Sajadi, Mohammad Taher Pilehvar

Stanza: A Python Natural Language Processing Toolkit for Many Human Languages (2020.acl-demos)

Challenge:	Existing tools for Persian language processing are based on conventional non-neural models and do not take full advantage of the latest developments.
Approach:	They propose to use a Python neural pipeline for Persian text processing tasks . they use 'parsBERT' to fine-tune the Python pipeline using the PerDT dataset .
Outcome:	The proposed toolkit can achieve state-of-the-art performance on multiple NLP tasks.

Copied to clipboard

Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, Christopher D. Manning

Challenge:	Existing tools that support only a few major languages are under-optimized for accuracy due to a focus on efficiency or use of less powerful models.
Approach:	They introduce a Python natural language processing toolkit that supports 66 languages . they train Stanza on 112 datasets and show it generalizes well on all languages compared to other tools .
Outcome:	The proposed toolkit performs well on 112 datasets and is compatible with the popular Java CoreNLP software.

Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages (2021.tacl-1)

Copied to clipboard

Edoardo M. Ponti, Ivan Vulić, Ryan Cotterell, Marinela Parovic, Roi Reichart, Anna Korhonen

Language Models

Challenge:	Currently, there are only 24 languages in the world that have not been annotated . transferring knowledge across domains is a common solution .
Approach:	They propose a Bayesian generative model for the space of neural parameters that factorizes into latent variables for each language and each task.
Outcome:	The proposed model can perform better than state-of-the-art methods with a typologically diverse sample of 33 languages from 4 continents and 11 families.

Cross-lingual Structure Transfer for Relation and Event Extraction (D19-1)

Copied to clipboard

Ananya Subburathinam, Di Lu, Heng Ji, Jonathan May, Shih-Fu Chang, Avirup Sil, Clare Voss

Multilinguality

Challenge:	Existing approaches to identify complex semantic structures are difficult to train from under-annotated sources.
Approach:	They exploit relation- and event-relevant language-universal features to train relation or event extractors from source annotations and apply them to target languages.
Outcome:	The proposed approach achieves comparable performance to state-of-the-art models trained on 3,000 manually annotated mentions.

Camelira: An Arabic Multi-Dialect Morphological Disambiguator (2022.emnlp-demos)

Copied to clipboard

Ossama Obeid, Go Inoue, Nizar Habash

Towards Unsupervised Morphological Analysis of Polysynthetic Languages (2022.aacl-short)

Challenge:	Camelira is a web-based Arabic multi-dialect morphological disambiguation tool that covers modern standard Arabic, Egyptian, Gulf, and Levantine.
Approach:	They propose a web-based Arabic multi-dialect morphological disambiguation tool that covers modern standard Arabic, Egyptian, Gulf, and Levantine.
Outcome:	The proposed tool covers modern standard Arabic, Egyptian, Gulf, and Levantine . it also provides an option to automatically choose an appropriate disambiguator based on the prediction of a dialect identification component.

Copied to clipboard

Sujay Khandagale, Yoann Léveillé, Samuel Miller, Derek Pham, Ramy Eskander, Cass Lowry, Richard Compton, Judith Klavans, Maria Polinsky, Smaranda Muresan

A Large Annotated Reference Corpus of New High German Poetry (2024.lrec-main)

Challenge:	Polysynthetic languages are low-resource, lacking large scale annotated datasets needed to build and/or evaluate computational models.
Approach:	They propose to use linguistic priors to help with morphological segmentation and part-of-speech tagging tasks for Adyghe and Inuktitut .
Outcome:	The proposed methods improve morphological segmentation and part-of-speech tagging tasks on Adyghe and Inuktitut.

Copied to clipboard

Thomas Haider

Challenge:	a corpus of public domain German poetry covering the time period 1600 to the 1920s contains 65k unique poems and over 1.6M lines, each tokenized, syllabified, pos-tagged, and meter-tagged.
Approach:	They present a large annotated corpus of public domain German poetry covering the time period 1600 to the 1920s with 65k poems.
Outcome:	The corpus contains 65k unique poems and over 1.6M lines, each tokenized, syllabified, pos-tagged, and meter-tagged.

From Spelling to Grammar: A New Framework for Chinese Grammatical Error Correction (2022.findings-emnlp)

Copied to clipboard

Xiuyu Wu, Yunfang Wu

Mutual Information Maximization for Simple and Accurate Part-Of-Speech Induction (N19-1)

Challenge:	Chinese Grammatical Error Correction (CGEC) aims to generate correct sentences from erroneous sequences.
Approach:	They propose a zero-shot approach for spelling error correction that is simple but effective . they propose auxiliary task to predict POS sequence of target sentence .
Outcome:	The proposed framework achieves 42.11 F-0.5 on the English GEC dataset outperforms the previous state-of-the-art by a wide margin of 1.30 points.

Copied to clipboard

Karl Stratos

Language Models

Challenge:	Using stochastic gradient descent, part-of-speech (POS) induction is a challenging task.
Approach:	They propose to maximize mutual information between the induced label and its context by maximizing mutual information.
Outcome:	The proposed approach achieves strong performance on a multitude of datasets and languages with a simple architecture that encodes morphology and context.

Conditional probing: measuring usable information beyond a baseline (2021.emnlp-main)

Copied to clipboard

John Hewitt, Kawin Ethayarajh, Percy Liang, Christopher Manning

Leveraging a Bilingual Dictionary to Learn Wolastoqey Word Representations (2022.lrec-1)

Challenge:	Existing methods for probing representations are limited to predicting part-of-speech . current methods cannot detect when a representation is predictive of just aspects of part- of-seech not explainable by the word identity.
Approach:	They propose to condition on the information in a baseline representation to test whether it is predictive of part-of-speech.
Outcome:	The proposed method is based on a theory of usable information called V-information and conditions on the information in the baseline.

Copied to clipboard

Diego Bear, Paul Cook

Unsupervised Learning of Syntactic Structure with Invertible Neural Projections (D18-1)

Challenge:	Existing word embeddings for lowresource languages require large corpora of running text to learn high quality representations.
Approach:	They leverage a bilingual dictionary to learn Wolastoqey word embeddings by encoding their corresponding English definitions into vector representations using pretrained English word and sequence representation models.
Outcome:	The proposed model outperforms baseline models without language-specific training or fine-tuning.

Copied to clipboard

Junxian He, Graham Neubig, Taylor Berg-Kirkpatrick

BanglaAutoKG: Automatic Bangla Knowledge Graph Construction with Semantic Neural Graph Filtering (2024.lrec-main)

Challenge:	Unsupervised learning of syntactic structure is typically performed using generative models with discrete latent variables and multinomial parameters.
Approach:	They propose a generative model that jointly learns discrete syntactic structure and continuous word representations in an unsupervised fashion by cascading an invertible neural network with a structured generative prior.
Outcome:	The proposed model outperforms state-of-the-art models on part-of speech (POS) induction and unsupervised dependency parsing without gold POS annotation.

Copied to clipboard

Azmine Toushik Wasi, Taki Hasan Rafi, Raima Islam, Dong-Kyu Chae

Structured Data in NLP

Challenge:	Bangla is underrepresented in KGs due to lack of comprehensive datasets, encoders, NER models, part-of-speech taggers, and lemmatizers.
Approach:	Bangla is underrepresented in KGs due to lack of comprehensive datasets, encoders, NER models, part-of-speech taggers, and lemmatizers. authors propose a framework that can automatically construct Bengali KG from any Bangla text.
Outcome:	The proposed framework can automatically construct Bengali KGs from any Bangla text.

Part-of-Speech Tagging on an Endangered Language: a Parallel Griko-Italian Resource (C18-1)

Copied to clipboard

Antonios Anastasopoulos, Marika Lekakou, Josep Quer, Eleni Zimianiti, Justin DeBenedetto, David Chiang

Tagging

Challenge:	a recent study examines POS tagging techniques on endangered languages . most natural language processing applications have been tested on only a handful of languages - a problem that is compounded by the lack of standard orthography.
Approach:	They evaluate POS tagging techniques on an endangered language, Griko . they use a semi-supervised method with cross-lingual transfer to achieve better accuracy .
Outcome:	The proposed method achieves 72.9% accuracy on a sample of 114 narratives in a language . the proposed method improves by 21 percentage points over previous methods .

Word Embedding Evaluation for Sinhala (2020.lrec-1)

Copied to clipboard

Dimuthu Lakmal, Surangika Ranathunga, Saman Peramuna, Indu Herath

Unsupervised Stem-based Cross-lingual Part-of-Speech Tagging for Morphologically Rich Low-Resource Languages (2022.naacl-main)

Challenge:	Word embeddings are a key component of the natural language processing process.
Approach:	They evaluate three standard word embedding models for Sinhala language using two evaluation methods: intrinsic evaluation and extrinsic evaluation.
Outcome:	The proposed models performed best in the three evaluation tasks, while FastText and Glove showed the lowest accuracies.

Copied to clipboard

Ramy Eskander, Cass Lowry, Sujay Khandagale, Judith Klavans, Maria Polinsky, Smaranda Muresan

Evaluating the Utility of Hand-crafted Features in Sequence Labelling (D18-1)

Challenge:	Low-resource languages lack annotated data even for basic syntactic information such as parts of speech.
Approach:	They propose an unsupervised cross-lingual approach for POS tagging for low-resource languages of rich morphology . they further investigate morpheme-level alignment and projection and use of linguistic priors for morphological segmentation .
Outcome:	The proposed approach outperforms the word-based approach and outperfies word-driven approaches.

Copied to clipboard

Minghao Wu, Fei Liu, Trevor Cohn

Language Models

Challenge:	Conventional wisdom is that hand-crafted features are redundant for deep learning models . authors propose a method for using handcrafted features in a hybrid learning approach .
Approach:	They propose a method for exploiting handcrafted features as part of a hybrid learning approach.
Outcome:	The proposed method outperforms baseline models on a named entity recognition task and reduces training requirements to 60% while maintaining the same predictive accuracy.

Cross-Lingual Syntactic Transfer through Unsupervised Adaptation of Invertible Projections (P19-1)

Copied to clipboard

Junxian He, Zhisong Zhang, Taylor Berg-Kirkpatrick, Graham Neubig

The interplay between language similarity and script on a novel multi-layer Algerian dialect corpus (2021.findings-acl)

Challenge:	Current systems for syntactic analysis tasks rely heavily on large scale annotated data.
Approach:	They propose to learn a generative model with a structured prior that uses labeled source and unlabeled target data jointly.
Outcome:	The proposed model improves on part-of-speech tagging and dependency parsing tasks on English as the only source corpus and on a wide range of target languages.

Copied to clipboard

Samia Touileb, Jeremy Barnes

Multilinguality

Challenge:	Recent studies have focused on cross-lingual transfer between languages with similar typology and languages of different scripts.
Approach:	They propose to annotate Algerian user-generated comments with parallel annotations . they also investigate the effect of script vs. language similarity in cross-lingual transfer .
Outcome:	The proposed model fine-tunes multi-lingual models on Algerian language and scripts . it shows that script vs. language similarity is important for part-of-speech tagging and sentiment analysis .

Palmyra: A Platform Independent Dependency Annotation Tool for Morphologically Rich Languages (L18-1)

Copied to clipboard

Talha Javed, Nizar Habash, Dima Taji

Moving TIGER beyond Sentence-Level (L18-1)

Challenge:	PALMYRA is an annotation tool designed to help with syntactic annotation of morphologically rich languages.
Approach:	They present PALMYRA, a platform independent graphical dependency tree visualization and editing software.
Outcome:	PALMYRA is an graphical dependency tree visualization and editing software designed to support syntactic annotation of morphologically rich languages.

Copied to clipboard

Agnieszka Falenska, Kerstin Eckart, Jonas Kuhn

Unsupervised Cross-Lingual Part-of-Speech Tagging for Truly Low-Resource Scenarios (2020.emnlp-main)

Challenge:	TIGER 2.2-doc is a new set of annotations for the German TIger corpus.
Approach:	They propose a new set of annotations for the German TIGER corpus . they introduce new document-level annotations: authors and their gender.
Outcome:	The new annotations improve the TIGER corpus and its structure and authors and gender.

Copied to clipboard

Ramy Eskander, Smaranda Muresan, Michael Collins

Another Dead End for Morphological Tags? Perturbed Inputs and Parsing (2023.findings-acl)

Challenge:	a limited set of translations into one or more high-resource languages are available for POS tagging . a bi-LSTM architecture that uses contextualized word embeddings improves performance .
Approach:	They propose an unsupervised cross-lingual transfer approach for part-of-speech tagging . they use the Bible as parallel data to learn POS taggers for target languages .
Outcome:	The proposed approach improves accuracy on 12 diverse languages . the Bible is used as a parallel corpus for the study .

Copied to clipboard

Alberto Muñoz-Ortiz, David Vilares

ELLEN: Extremely Lightly Supervised Learning for Efficient Named Entity Recognition (2024.lrec-main)

Challenge:	Part-of-speech tags are used for word-contextualized parsers, but their impact is limited to word-based models.
Approach:	They propose an adversarial attack to test whether morphological tags contribute to error propagation or correct parsing mistakes.
Outcome:	The proposed attack on 14 treebanks shows that if morphological tags were utopically robust against lexical perturbations, they would be able to correct parsing mistakes.

Copied to clipboard

Haris Riaz, Razvan Gabriel Dumitru, Mihai Surdeanu

Language Modelling Makes Sense: Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation (P19-1)

Challenge:	Named entity recognition (NER) tasks require an amount of annotations that are unrealistic for many real-world applications.
Approach:	They propose a semi-supervised named entity recognition method that blends language models with linguistic rules.
Outcome:	The proposed method outperforms most existing semi-supervised methods under the same supervision settings commonly used in the literature.

Copied to clipboard

Daniel Loureiro, Alípio Jorge

Collection and Analysis of Code-switch Egyptian Arabic-English Speech Corpus (L18-1)

Challenge:	Contextual embeddings address the problem of meaning conflation hampering word embeddables.
Approach:	They propose a method that creates sense-level embeddings with full-coverage of WordNet without recourse to explicit sense distributions or task-specific modelling.
Outcome:	The proposed method surpasses previous systems using powerful models and is robust when ignoring part-of-speech and lemma features.

Copied to clipboard

Injy Hamed, Mohamed Elmahdy, Slim Abdennadher

Dialogue Systems & Conversational Agents

Challenge:	despite of the great demand, there is still a huge shortage in available corpora for dialectal languages and code-switched speech.
Approach:	They collect conversational Egyptian Arabic spontaneous speech, extract transcriptions and analyze it from a code-switching perspective.
Outcome:	The authors collect conversational Egyptian Arabic spontaneous speech, extract transcriptions and analyze speech from the code-switching perspective.

A Morphologically Annotated Corpus of Emirati Arabic (L18-1)

Copied to clipboard

Salam Khalifa, Nizar Habash, Fadhl Eryani, Ossama Obeid, Dana Abdulrahim, Meera Al Kaabi

A Gold Standard Dependency Treebank for Turkish (2020.lrec-1)

Challenge:	Emirati Arabic corpus is first large-scale morphologically manually annotated corpus . resources for dialectal Arabic NLP tasks are still lacking compared to those for modern standard Arabic (MSA).
Approach:	They propose to annotate a large-scale corpus of Emirati Arabic using a morphologically manually annotated corpus from eight Gumar novels . they discuss the guidelines for each part of the annotation components, and the annotation interface they use.
Outcome:	The annotated corpus includes about 200,000 words from eight Gumar novels in the Emirati Arabic variety.

Copied to clipboard

Tolga Kayadelen, Adnan Ozturel, Bernd Bohnet

Statistical Analysis of Missing Translation in Simultaneous Interpretation Using A Large-scale Bilingual Speech Corpus (L18-1)

Challenge:	Currently, Turkish treebanks are limited due to the limited number of annotated sentences in the domains of Wikipedia and ITU Web Treebanks.
Approach:	They propose to annotate Turkish web and Wikipedia sentences for segmentation, morphology, part-of-speech and dependency relations using tagsets and a Wikipedia section.
Outcome:	The proposed treebank is the largest publicly available morpho-syntactic treebank in terms of word count and has a dedicated Wikipedia section.

Copied to clipboard

Zhongxi Cai, Koichiro Ryu, Shigeki Matsubara

Multilinguality

Challenge:	Various types of omissions have been described in simultaneous interpretation to improve interpretation quality or train interpreters.
Approach:	They analyze missing translations in simultaneous interpretations using a large-scale bilingual speech corpus.
Outcome:	The authors found that a high proportion of adverbs were missed in the translations . the authors suggest that omissions can be improved to improve interpretation quality .

LaoPLM: Pre-trained Language Models for Lao (2022.lrec-1)

Copied to clipboard

Nankai Lin, Yingwen Fu, Chuwei Chen, Ziyu Yang, Shengyi Jiang

An Empirical Study on Leveraging Position Embeddings for Target-oriented Opinion Words Extraction (2021.emnlp-main)

Challenge:	Pre-trained language models (PLMs) can capture different levels of concepts in context . previous work on Lao has been hampered by the lack of annotated datasets .
Approach:	They construct a text classification dataset to alleviate the resource-scarce situation of Lao . they evaluate them on two downstream tasks: part-of-speech tagging and text classification .
Outcome:	The proposed model can capture different levels of concepts in context and generate universal language representations.

Copied to clipboard

Samuel Mensah, Kai Sun, Nikolaos Aletras

Consonant is all you need: a compact representation of English text for efficient NLP (2023.findings-emnlp)

Challenge:	Current methods for extracting opinion words for an aspect in text leverage position embeddings to capture relative position of word to the target.
Approach:	They propose to use pretrained word embeddings to extract opinion words for a given aspect in text.
Outcome:	The proposed methods outperform current methods on a task based on pre-trained word embeddings and position embedders.

Copied to clipboard

Maged Al-shaibani, Irfan Ahmad