Croatia

Embedding representations of text are useful for downstream natural language processing tasks. Several universal sentence representation methods have been proposed with a particular focus on self-supervised pre-training approaches to leverage the vast quantities of unlabelled data. However, there are two challenges for generating rich embedding representations for a new document. 1) The latest rich embedding generators are based on very large costly transformer-based architectures. 2) The rich embedding representation of a new document is limited to only the information provided without access to any explicit contextual and temporal information that could potentially further enrich the representation. We propose efficient retrieval-augmented text embeddings (ERATE) that tackles the first issue and offers a method to tackle the second issue. To the best of our knowledge, we are the first to incorporate retrieval to general purpose embeddings as a new paradigm, which we apply to the semantic similarity tasks of SentEval. Despite not reaching state-of-the-art performance, ERATE offers key insights that encourages future work into investigating the potential of retrieval-based embeddings.

EACL 2023

ERATE: Efficient Retrieval Augmented Text Embeddings

text embeddings

text similarity

retrieval

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

workshop paper

### Welcome to the 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL) 
Continuing its mission of expanding and involving the science community of all European countries, EACL had selected the Ukrainian community for the 16th EACL, which took place online due to the COVID pandemic. Unfortunately, the ongoing war made the organisation in Kyiv impossible. Considering the importance of physical interaction among researchers, especially after the restrictions imposed by the COVID pandemic, in addition to an online mode, the conference will be held in Dubrovnik, Croatia, from 2 to 6 of May, 2023. The original aim of strengthening the connection with the Ukrainian community will not change as our program will feature a dedicated session and a workshop to highlight work on Ukrainian language technologies. As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

You need to register for the conference in order to access this site. Please visit https://2023.eacl.org/registration for more information.

As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

In this paper, we describe how we unearthed some fundamental problems while building an analogy dataset to evaluate historical Irish embeddings on their ability to detect orthographic, morphological and semantic similarity. Low agreement among field experts and the absence of an editorial standard in available resources make it impossible to build reliable evaluation datasets for computational models and obtain interpretable results. We emphasise the need for a historical text editing standard, particularly for NLP applications, and prompt Celticists and historical linguists to engage in further discussion. We would also like to draw NLP scholars' attention to the role of data and its (extra)linguistic properties in testing new models and evaluation scenarios.

Do not Trust the Experts: How the Lack of Standard Complicates NLP for Historical Irish

Despite recent successes in language models, their ability to represent numbers is insufficient. Humans conceptualize numbers based on their magnitudes, effectively projecting them on a number line; whereas subword tokenization fails to explicitly capture magnitude by splitting numbers into arbitrary chunks. To alleviate this shortcoming, alternative approaches have been proposed that modify numbers at various stages of the language modeling pipeline. These methods change either the (1) notation in which numbers are written (\eg scientific vs decimal), the (2) vocabulary used to represent numbers or the entire (3) architecture of the underlying language model, to directly regress to a desired number.

Previous work \cite{berg-kirkpatrick-spokoyny-2020-empirical} suggests that architectural change helps achieve state-of-the-art on number estimation but we find an insightful ablation: changing the model's vocabulary instead (\eg introduce a new token for numbers in range 10-100) is a far better trade-off. In the context of masked number prediction, a carefully designed tokenization scheme is both the simplest to implement and sufficient, \ie with similar performance to the state-of-the-art approach that requires making significant architectural changes. Finally, we report similar trends on the downstream task of numerical fact estimation (for Fermi Problems) and discuss reasons behind our findings.

Estimating Numbers without Regression

Collecting high quality conversational data can be very expensive for most applications and infeasible for others due to privacy, ethical, or similar concerns. A promising direction to tackle this problem is to generate synthetic dialogues by prompting large language models. In this work, we use a small set of expert-written conversations as incontext examples to synthesize a social conversation dataset using prompting 1. We perform several thorough evaluations of our synthetic conversations compared to human-collected conversations. This includes various dimensions of conversation quality with human evaluation directly on the synthesized conversations, and interactive human evaluation of chatbots fine-tuned on the synthetically generated dataset. We additionally demonstrate that this prompting approach is generalizable to multiparty conversations, providing potential to create new synthetic data for multi-party tasks. Our synthetic multi-party conversations were rated more favorably across all measured dimensions compared to conversation excerpts sampled from a human-collected multi-party dataset.

PLACES: Prompting Language Models for Social Conversation Synthesis

We report our efforts in identifying a set of previous human evaluations in NLP that would be suitable for a coordinated study examining what makes human evaluations in NLP more/less reproducible. We present our results and findings, which include that just 13% of papers had (i) sufficiently low barriers to reproduction, and (ii) enough obtainable information, to be considered for reproduction and that all but one of the experiments we selected for reproduction was discovered to have flaws that made the meaningfulness of conducting a reproduction questionable. As a result, we had to change our coordinated study design from a reproduce approach to a standardise-then-reproduce-twice approach. Our overall (negative) finding that the great majority of human evaluations in NLP is not repeatable and/or not reproducible and/or too flawed to justify reproduction, paints a dire picture, but presents an opportunity for a rethink about how to design and report human evaluations in NLP.

Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human

Existing language and vision models achieve impressive performance in image-text understanding. Yet, it is an open question to what extent they can be used for language understanding in 3D environments and whether they implicitly acquire 3D object knowledge, e.g. about different views of an object.
In this paper, we investigate whether a state-of-the-art language and vision model, CLIP, is able to ground perspective descriptions of a 3D object and identify canonical views of common objects based on text queries.
We present an evaluation framework that uses a circling camera around a 3D object to generate images from different viewpoints and evaluate them in terms of their similarity to natural language descriptions.
We find that a pre-trained CLIP model performs poorly on most canonical views and that fine-tuning using hard negative sampling and random contrasting yields good results even under conditions with little available training data.

Paparazzi: A Deep Dive into the Capabilities of Language and Vision Models for Grounding Viewpoint Descriptions

Dialect Identification is a crucial task for localizing various Large Language Models. This paper outlines our approach to the VarDial 2023 DSL-TL shared task. Here we have to identify three or two dialects from three languages each which results in a 9-way classification for Track-1 and 6-way classification for Track-2 respectively. Our proposed approach consists of a two-stage system and outperforms other participants’ systems and previous works in this domain. We achieve a score of 58.54% for Track-1 and 85.61% for Track-2. Our codebase is available publicly.

Two-stage Pipeline for Multilingual Dialect Detection

In this work, we induce character-level noise in various forms when fine-tuning BERT to enable zero-shot cross-lingual transfer to unseen dialects and languages. We fine-tune BERT on three sentence-level classification tasks and evaluate our approach on an assortment of unseen dialects and languages. We find that character-level noise can be an extremely effective agent of cross-lingual transfer under certain conditions, while it is not as helpful in others. Specifically, we explore these differences in terms of the nature of the task and the relationships between source and target languages, finding that introduction of character-level noise during fine-tuning is particularly helpful when a task draws on surface level cues and the source-target cross-lingual pair has a relatively high lexical overlap with shorter (i.e., less meaningful) unseen tokens on average.

Fine-Tuning BERT with Character-Level Noise for Zero-Shot Transfer to Dialects and Closely-Related Languages

Hate speech detection in online platforms has been widely studied in the past. Most of these works were conducted in English and a few rich-resource languages. Recent approaches tailored for low-resource languages have explored the interests of zero shot cross-lingual transfer learning models in resource-scarce scenarios. However, languages variations between geolects such as American English and British English, Latin-American Spanish, and European Spanish is still a problem for NLP models that often relies on (latent) lexical information for their classification tasks. More importantly, the cultural aspect, crucial for hate speech detection, is often overlooked.

In this work, we present the results of a thorough analysis of hate speech detection models performance on different variants of Spanish, including a new hate speech toward immigrants Twitter data set we built to cover these variants. Using mBERT and Beto, a monolingual Spanish Bert-based language model, as the basis of our transfer learning architecture, our results indicate that hate speech detection models for a given Spanish variant are affected when different variations of such language are not considered. Hate speech expressions could vary from region to region where the same language is spoken.

Analyzing Zero-Shot transfer Scenarios across Spanish variants for Hate Speech Detection

Pre-trained models usually come with a pre-defined tokenization and little flexibility as to what subword tokens can be used in downstream tasks. This problem concerns especially multilingual NLP and low-resource languages, which are typically processed using cross-lingual transfer. In this paper, we aim to find out if the right granularity of tokenization is helpful for a text classification task, namely dialect classification. Aiming at generalizations beyond the studied cases, we look for the optimal granularity in four dialect datasets, two with relatively consistent writing (one Arabic and one Indo-Aryan set) and two with con- siderably inconsistent writing (one Arabic and one Swiss German set). To gain more control over subword tokenization and ensure direct comparability in the experimental settings, we train a CNN classifier from scratch comparing two subword tokenization methods (Unigram model and BPE). For reference, we compare the results obtained in our analysis to the state of the art achieved by fine-tuning pre-trained models. We show that models trained from scratch with an optimal tokenization level perform better than fine-tuned classifiers in the case of highly inconsistent writing. In the case of relatively consistent writing, fine-tuned mod- els remain better regardless of the tokenization level.

Optimizing the Size of Subword Vocabularies in Dialect Classification

Eye-tracking data in Chinese languages present unique challenges due to the non-alphabetic and unspaced nature of the Chinese writing systems. This paper introduces the first deeply-annotated joint Mandarin-Cantonese eye-tracking dataset, from which we achieve a unified eye-tracking prediction system for both language varieties. In addition to the commonly studied first fixation duration and the total fixation duration, this dataset also includes the second fixation duration, expressing fixation patterns that are more relevant to higher-level, structural processing. 

A basic comparison of the features and measurements in our dataset revealed variation between Mandarin and Cantonese on fixation patterns related to word class and word position. The test of feature usefulness suggested that traditional features are less powerful in predicting the second-pass fixation, to which the linear distance to root makes a leading contribution in Mandarin. In contrast, Cantonese eye-movement behavior relies more on word position and part of speech.

Downloads

Next from EACL 2023

Do not Trust the Experts: How the Lack of Standard Complicates NLP for Historical Irish

Similar lecture

Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective