Papers with Tagging
Recognizing Complex Entity Mentions: A Review and Future Directions (P18-3)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is a task of identifying and classifying named entities (NE) within text. |
| Approach: | They review existing methods for identifying and classifying named entities within text . they identify the research gap and propose a new approach to tackle these problems . |
| Outcome: | The proposed methods address the identified identified gaps in the literature and provide recommendations for future work. |
AlpacaTag: An Active Learning-based Crowd Annotation Framework for Sequence Tagging (P19-3)
Copied to clipboard
| Challenge: | Existing sequence annotation tools focus on improving user interfaces and user interface. |
| Approach: | They propose an open-source web-based data annotation framework for sequence tagging tasks . the framework is based on active learning and automatic crowd consolidation . |
| Outcome: | The proposed framework is a comprehensive solution for sequence labeling tasks . it can be deployed in downstream systems while new annotations are being made . |
Effort Estimation in Named Entity Tagging Tasks (2020.lrec-1)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) requires large amounts of annotated data. |
| Approach: | They investigate which variables influence the time spent on a named entity annotation task by a human . they found a root mean squared error (RMSE) of 25.68 words per minute with a Nearest Neighbors model . |
| Outcome: | The proposed model achieves a root mean squared error (RMSE) of 25.68 words per minute with a Nearest Neighbors model. |
Sentence Level Temporality Detection using an Implicit Time-sensed Resource (L18-1)
Copied to clipboard
| Challenge: | Temporal sense detection of any word is an important aspect for detecting temporality at the sentence level. |
| Approach: | They build a temporal resource based on a semi-supervised learning approach . they use past, present, future, neutral and atemporal senses to tag sentences . |
| Outcome: | The proposed resource is based on a semi-supervised learning approach . it is used to tag sentences with past, present and future temporal senses . |
Generative Models for Product Attribute Extraction (2023.emnlp-industry)
Copied to clipboard
| Challenge: | generative models are used for product attribute extraction, a new field in information extraction and e-commerce. |
| Approach: | They analyze generative models for product attribute extraction and demonstrate their utility . they perform experiments on Amazon and MAVE product attribute datasets . |
| Outcome: | The proposed model can generate implicit attribute values, which state-of-the-art models are unable to extract. |
Distant Supervision from Disparate Sources for Low-Resource Part-of-Speech Tagging (D18-1)
Copied to clipboard
| Challenge: | Low-resource languages lack manual annotated data to learn basic models such as part-of-speech (POS) taggers. |
| Approach: | They propose a cross-lingual neural part-of-speech tagger that learns from disparate sources of distant supervision in a uniform framework. |
| Outcome: | The proposed model scales to hundreds of low-resource languages without access to gold annotated data. |
A Bayesian Approach for Sequence Tagging with Crowds (D19-1)
Copied to clipboard
| Challenge: | Existing methods for sequence tagging are data hungry and annotators are unreliable . current methods do not account for common types of span annotation error . |
| Approach: | They propose a Bayesian method for aggregating sequence tags that models sequential dependencies between annotations and ground-truth labels. |
| Outcome: | The proposed method outperforms existing methods on crowdsourced data and reduces crowdsourcing costs through active learning. |
SoMeWeTa: A Part-of-Speech Tagger for German Social Media and Web Texts (L18-1)
Copied to clipboard
| Challenge: | Off-the-shelf part-of-speech taggers perform poorly on web and social media data . this is due to the many unconventional spelling variants that occur in web and twitter texts and that result in a high proportion of out-of vocabulary words. |
| Approach: | They propose to use TIGER corpus as a part-of-speech tagger to train a German part- of-speak tagger on the web and social media data of the EmpiriST 2015 shared task. |
| Outcome: | The proposed tagger significantly improves on the state-of-the-art for both the web and social media data. |
Extracting Victim Counts from Text (2023.eacl-main)
Copied to clipboard
| Challenge: | Using tagging and regex methods, data on injured, displaced, or abused victims is difficult . data on earthquake injuries and deaths is scarce, subjective, or biased . |
| Approach: | They compare tagging approaches to extract injured, displaced, or abused victims . they discuss calibration and investigate out-of-distribution and few-shot performance . |
| Outcome: | The proposed model is among the first to apply numeracy-focused large language models in a real-world use case with a positive impact. |
Improving Large-Scale Fact-Checking using Decomposable Attention Models and Lexical Tagging (D18-1)
Copied to clipboard
| Challenge: | Existing pipelines for fact-checking of textual sources are limited . fact- checking of text sources requires a large knowledge base to extract relevant information . |
| Approach: | They propose a neural ranker that dynamically selects sentences to improve evidence retrieval . they incorporate lexical tagging methods into the pipeline framework to simplify the tasks . |
| Outcome: | The proposed model outperforms the existing TF-IDF method on a large-scale fact extraction and verification dataset with speedup. |
Decoding Part-of-Speech from Human EEG Signals (2022.acl-long)
Copied to clipboard
| Challenge: | Recent studies have shown that EEG signal magnitude and topography depend on word length, frequency and open vs. closed class. |
| Approach: | They propose to use EEG to predict Part-of-Speech (PoS) tags from neural signals measured at millisecond resolution during text reading. |
| Outcome: | The proposed techniques outperform linear-SVMs on PoS tagging of unigram and bigram data. |
Towards a Welsh Semantic Annotation System (L18-1)
Copied to clipboard
| Challenge: | Automatic semantic annotation of natural language data is an important task in Natural Language Processing. |
| Approach: | They develop a Welsh semantic annotation tool that can be used to analyze Welsh text . it uses Lancaster's USAS semantic classification scheme to tag words with semantic tags . |
| Outcome: | The proposed tool can cover up to 91.78% of words in Welsh 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
| 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 . |
MPST: A Corpus of Movie Plot Synopses with Tags (L18-1)
Copied to clipboard
| Challenge: | a corpus of movie plot synopses and tags can be used to build automatic tagging systems . a method to collect these tags allows us to learn to predict tags from plot synoopsis . |
| Approach: | They propose to collect a corpus of movie plot synopses and 70 tags to analyze their properties. |
| Outcome: | The proposed method can be used to predict movie tags from plot synopses. |
Leveraging Order-Free Tag Relations for Context-Aware Recommendation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to tag recommendation neglect orderlessness and inter-dependency . Empirical results on Instagram and Stack Overflow show that our method is significantly superior to the previous approaches. |
| Approach: | They propose a sequence-oblivious generation method for tag recommendation . the next tag to be generated is independent of the order of the generated tags . they also propose regressive generation methods that take orderlessness into account . |
| Outcome: | Empirical results show that the proposed method is superior to previous approaches . the proposed system is based on two domains, Instagram and Stack Overflow . |
On the Way to Gentle AI Counselor: Politeness Cause Elicitation and Intensity Tagging in Code-mixed Hinglish Conversations for Social Good (2024.findings-naacl)
Copied to clipboard
| Challenge: | Politeness is a multifaceted concept influenced by individual perceptions of what is considered polite or impolite. |
| Approach: | They propose a task to identify the underlying reasons behind the use of politeness and gauge the degree of politity conveyed. |
| Outcome: | The proposed method is compared against state-of-the-art datasets and their results show it is superior. |
Towards a Corsican Basic Language Resource Kit (2020.lrec-1)
Copied to clipboard
| Challenge: | a roadmap has been set out for the development of a basic language resource kit for the Corsican language . the goal is to improve the availability of resources and tools for the language based on the Banque de Données Langue Corse project . |
| Approach: | a team of researchers from univ-corse is developing a basic language resource kit for the corsican language . they aim to collect corpora, set up a concordancer, set-up language detection tool, build an electronic dictionary and add a part-of-speech tagger . |
| Outcome: | the goal is to improve the availability of resources and tools for the Corsican language . the roadmap sets out the actions to be undertaken: collection of corpora, setting up of a concordancer, language detection tool, electronic dictionary and part-of-speech tagger. |
An Empirical Evaluation of Annotation Practices in Corpora from Language Documentation (2020.lrec-1)
Copied to clipboard
| Challenge: | Language documentation projects have produced substantial amounts of primary data from a wide variety of endangered languages. |
| Approach: | They propose to use common annotation conventions in existing corpora to facilitate their future processing. |
| Outcome: | The proposed formats are based on the common ELAN and Toolbox formats and are used to facilitate their future processing. |
GeCoTagger: Annotation of German Verb Complements with Conditional Random Fields (L18-1)
Copied to clipboard
| Challenge: | Complement phrases are essential for constructing well-formed sentences in German. |
| Approach: | They propose an algorithm which can identify and classify complement phrases of any German verb in any written sentence context. |
| Outcome: | The proposed algorithm can identify and classify complement phrases of any German verb in any written sentence context. |
Part-of-Speech Tagging for Code-Switched, Transliterated Texts without Explicit Language Identification (D18-1)
Copied to clipboard
| Challenge: | Code-switching is a challenge for NLP due to the lack of representative data for training models. |
| Approach: | They propose a model that is trained exclusively on monolingual resources but can be applied to unseen code-switched text at inference time. |
| Outcome: | The proposed model outperforms standard models on Hindi-English part-of-speech tagging and on unannotated code-switched text with alternate scripts. |
Inducing Universal Semantic Tag Vectors (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing semantic tags are useful for syntactically oriented downstream NLP tasks . but their size is limited and many words are out-of-vocabulary words . |
| Approach: | They propose to tagging words with semantic distinctions that are likely to be useful across semantic tasks. |
| Outcome: | The proposed semantic tagging scheme can predict unseen words with high accuracy . it distinguishes privative attributes from subsective ones, making it easier to discern fake detectives . |
Making Heads and Tails of Models with Marginal Calibration for Sparse Tagsets (2021.findings-emnlp)
Copied to clipboard
| Challenge: | despite high accuracy, modern neural networks can still suffer from severe miscalibration. |
| Approach: | They propose to use tag frequency grouping to measure calibration error in different frequency bands to reduce error. |
| Outcome: | The proposed techniques reduce calibration error across the marginal distribution for two existing sequence taggers. |
Part-Of-Speech Sensitivity of Routers in Mixture of Experts Models (2025.coling-main)
Copied to clipboard
| Challenge: | a study examines the behavior of routers in Mixture of Experts (MoE) models . experts with similar linguistic traits are often routed to the same expert regardless of context . |
| Approach: | They investigate how tokens are routed based on their linguistic features . they aim to explore whether experts specialize in processing tokens with similar linguistic traits . |
| Outcome: | The proposed model-integrated routers are based on Mixture of Experts (MoE) models . the results show that expert specialization is high for POS categories . |
#HowYouTagTweets: Learning User Hashtagging Preferences via Personalized Topic Attention (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods based on latent topics cannot capture user interests and thus can't be used to predict how likely a user will post with a hashtag. |
| Approach: | They propose a personalized topic attention model that captures salient contents to personalize hashtag contexts by predicting how likely a user will post with a hashtag. |
| Outcome: | The proposed model significantly outperforms the state-of-the-art recommendation approach without exploiting latent topics. |
The brWaC Corpus: A New Open Resource for Brazilian Portuguese (L18-1)
Copied to clipboard
| Challenge: | a large corpus for Brazilian Portuguese is needed for NLP applications . the corpus is 2.7 billion tokens, and domain diversity is maximized . |
| Approach: | They propose to build a large Web corpus for Brazilian Portuguese with 2.7 billion tokens . they also propose an updated sentence-level approach for the strict removal of duplicated content . |
| Outcome: | The proposed corpus is based on a pipeline methodology and is available for querying and downloading. |