Related papers: Tagging the Teleman Corpus
This paper presents an ensemble part-of-speech tagging approach for source code identifiers. Ensemble tagging is a technique that uses machine-learning and the output from multiple part-of-speech taggers to annotate natural language text at…
We present LemmaTag, a featureless neural network architecture that jointly generates part-of-speech tags and lemmas for sentences by using bidirectional RNNs with character-level and word-level embeddings. We demonstrate that both tasks…
We use a Dynamic Bayesian Network to represent compactly a variety of sublexical and contextual features relevant to Part-of-Speech (PoS) tagging. The outcome is a flexible tagger (LegoTag) with state-of-the-art performance (3.6% error on a…
The sarcasm detection task in natural language processing tries to classify whether an utterance is sarcastic or not. It is related to sentiment analysis since it often inverts surface sentiment. Because sarcastic sentences are highly…
Syntactic annotation of corpora in the form of part-of-speech (POS) tags is a key requirement for both linguistic research and subsequent automated natural language processing (NLP) tasks. This problem is commonly tackled using machine…
We investigate multi-speaker speech recognition from ultrasound images of the tongue and video images of the lips. We train our systems on imaging data from modal speech, and evaluate on matched test sets of two speaking modes: silent and…
Language Models have demonstrated remarkable capabilities on some tasks while failing dramatically on others. The situation has generated considerable interest in understanding and comparing the capabilities of various Language Models (LMs)…
Sense tagging, the automatic assignment of the appropriate sense from some lexicon to each of the words in a text, is a specialised instance of the general problem of semantic tagging by category or type. We discuss which recent word sense…
We conduct a large-scale fine-grained comparative analysis of machine translations (MT) against human translations (HT) through the lens of morphosyntactic divergence. Across three language pairs and two types of divergence defined as the…
We introduce Telegraph English (TE), a prompt-compression protocol that rewrites natural language into a symbol-rich, formally-structured dialect. Where token-deletion methods such as LLMLingua-2 train a classifier to delete low-importance…
By using a trigram model and fine-tuning a pretrained BERT model for sequence classification, we show that machine translation and human translation can be classified with an accuracy above chance level, which suggests that machine…
In the presented study, we discover that the so-called "transition freedom" metric appears superior for unsupervised tokenization purposes in comparison to statistical metrics such as mutual information and conditional probability,…
Part of speech tagging is a fundamental NLP task often regarded as solved for high-resource languages such as English. Current state-of-the-art models have achieved high accuracy, especially on the news domain. However, when these models…
This paper explores morpho-syntactic ambiguities for French to develop a strategy for part-of-speech disambiguation that a) reflects the complexity of French as an inflected language, b) optimizes the estimation of probabilities, c) allows…
This paper gives an overview of current trends in manual indexing on the Web. Along with a general rise of user generated content there are more and more tagging systems that allow users to annotate digital resources with tags (keywords)…
Spoken term detection (STD) is often hindered by reliance on frame-level features and the computationally intensive DTW-based template matching, limiting its practicality. To address these challenges, we propose a novel approach that…
Being able to rank the similarity of short text segments is an interesting bonus feature of neural machine translation. Translation-based similarity measures include direct and pivot translation probability, as well as translation…
Norms are challenging to define and measure, but this paper takes advantage of text data and the recent development in machine learning to create an encompassing measure of norms. An LSTM neural network is trained to detect gendered…
A prerequisite for the computational study of literature is the availability of properly digitized texts, ideally with reliable meta-data and ground-truth annotation. Poetry corpora do exist for a number of languages, but larger collections…
The development of Large Language Models (LLMs) relies on extensive text corpora, which are often unevenly distributed across languages. This imbalance results in LLMs performing significantly better on high-resource languages like English,…