Taiwan

Machine translation (MT) metrics often fail to achieve very high correlations with human assessments. In terms of MT system evaluation, most metrics pay equal attentions to every sample in an evaluation set, while in human evaluation, difficult sentences often make candidate systems distinguishable via notable fluctuations in human scores, especially when systems are competitive. We find that samples with high entropy values, which though usually count for less than 5%, tend to play a key role in MT evaluation: when the evaluation set is shrunk to only the high-entropy portion, correlations with human assessments are actually improved. Thus, in this paper, we propose a fast and unsupervised approach to enhance MT metrics using entropy, expanding the dimension of evaluation by introducing sentence-level difficulty. A translation hypothesis with a significantly high entropy value is considered difficult and receives a large weight in aggregation of system-level scores. Experimental results on five sub-tracks in the WMT19 Metrics shared tasks show that our proposed method significantly enhanced the performance of commonly-used MT metrics in terms of system-level correlations with human assessments, even outperforming existing SOTA metrics. In particular, all enhanced metrics exhibit overall stability in correlations with human assessments in circumstances where only competitive MT systems are included, while the corresponding standard metrics fail to correlate with human assessments.

IJCNLP-AACL 2022

Part Represents Whole: Improving the Evaluation of Machine Translation System Using Entropy Enhanced Metrics

sentence-level difficulty

system-level mt metric

machine translation evaluation

entropy

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

ACL-IJCNLP 2021

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

technical paper

The AACL, Asia-Pacific Chapter of the Association for Computational Linguistics, and the AFNLP, Asian Federation of Natural Language Processing, invite you to participate in the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL) and the 10th International Joint Conference on Natural Language Processing (IJCNLP). 
<br>
<br>

A registration is required to access this event. Access to the event site will be granted to all registered attendees on **November 16th**. If you have not already done so, please register using the link below:
<br>
<br>https://conference.iis.sinica.edu.tw/servlet/Register?ConferenceID=411

Registration Is Required

The AACL, Asia-Pacific Chapter of the Association for Computational Linguistics, and the AFNLP, Asian Federation of Natural Language Processing, invite you to participate in the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL) and the 10th International Joint Conference on Natural Language Processing (IJCNLP). 

Multiplex Networks and AI Unveil the Influence of the Mental Lexicon on Picture Naming and its Failures by People Struck with Aphasia

Object Naming is an important task within the field of Language and Vision that consists of generating a correct and appropriate name for an object given an image. The ManyNames dataset uses real-world human annotated images with multiple labels, instead of just one. In this work, we describe the adaptation of this dataset (originally in English) to Catalan, by (i) machine-translating the English labels and
(ii) collecting human annotations for a subset of the original corpus and comparing both resources. Analyses reveal divergences in the lexical variation of the two sets showing potential problems of directly translated resources, particularly when there is no resource to a proper context, which in this case is conveyed by the image. The analysis also points to the impact of cultural factors in the naming task, which
should be accounted for in future cross-lingual naming tasks.

CAT ManyNames: A New Dataset for Object Naming in Catalan.

The Thesaurus Linguae Latinae (TLL) is a comprehensive monolingual dictionary that records contextualized meanings and usages of Latin words in antique sources at an unprecedented scale. We created a new dataset based on a subset of sense representations in the TLL, with which we finetuned the Latin BERT neural language model (Bamman and Burns, 2020) on a supervised Word Sense Disambiguation task. We observe that the contextualized BERT representations finetuned on TLL data score better than static embeddings used in a bidirectional LSTM classifier on the same dataset, and that our per-headword BERT models achieve higher and more robust performance than reported by Bamman and Burns (2020) based on data from a bilingual Latin dictionary. We discuss the differences in sense organizational principles between these two lexical resources, and report about our dataset construction and improved evaluation methodology.

Finetuning Latin BERT for Word Sense Disambiguation on the Thesaurus Linguae Latinae.

Definition modeling is the task to generate a valid definition for a given input term. This relatively novel task has been approached either with no context (i.e., given a word embedding alone) and, more recently, as word-in-context modeling. Despite their success, most works make little to no distinction between resources and their specific features (e.g., type and style of definitions, or quality of examples) when used for training. Given the high diversity lexicographic resources exhibit in terms of topic coverage, style and formal structure, it is desirable for downstream definition modeling to better understand which of them are better suited for the task. In this paper, we propose an empirical evaluation of the well-known lexical database WordNet, and specifically, its dictionary examples. We evaluate them both directly, by matching them against criteria for good dictionary writing, and indirectly, in the task of definition modeling. Our results suggest that WordNet’s dictionary examples could be improved by extending them in length, and incorporating prototypicality.

Putting WordNet’s Dictionary Examples in the Context of Definition Modelling: An Empirical Analysis.

A Frame-Based Model of Inherent Polysemy, Copredication and Argument Coercion.

VISCOSE - a Kanji Dictionary Enriched with VISual, COmpositional, and SEmantic Information.

We present three large-scale experiments on binary text matching classification task both in Chinese and English to evaluate the effectiveness and generalizability of random text perturbations as a data augmentation approach for NLP. It is found that the augmentation can bring both negative and positive effects to the test set performance of three neural classification models, depending on whether the models train on enough original training examples. This remains true no matter whether five random text editing operations, used to augment text, are applied together or separately. Our study demonstrates with strong implication that the effectiveness of random text perturbations is task specific and not generally positive.

Addresing Reproducibility in Natural Language Processing

Various approaches have been proposed for automated stance detection, including those that use machine and deep learning models and natural language processing techniques. However, their cross-dataset performance, the impact of sample size on performance, and experimental aspects such as runtime have yet to be compared, limiting what is known about the generalizability of prominent approaches. This paper presents a replication study of stance detection approaches on current benchmark datasets. Specifically, we compare six existing machine and deep learning stance detection models on three publicly available datasets. We investigate performance as a function of the number of samples, length of samples (word count), representation across targets, type of text data, and the stance detection models themselves. We identify the current limitations of these approaches and categorize their utility for stance detection under varying circumstances (e.g., size of text samples), which provides valuable insight for future research in stance detection.

Why sentence similarity benchmark is not predictive of application-oriented task performance?

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-tutorials.1/)


Efficient and Robust Knowledge Graph Construction

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-tutorials.3/)


Downloads

Next from IJCNLP-AACL 2022

Multiplex Networks and AI Unveil the Influence of the Mental Lexicon on Picture Naming and its Failures by People Struck with Aphasia

Similar lecture

Difficulty-Aware Machine Translation Evaluation

Stay up to date with the latest Underline news!

PRODUCT

COMPANY

RESOURCES

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from IJCNLP-AACL 2022

Multiplex Networks and AI Unveil the Influence of the Mental Lexicon on Picture Naming and its Failures by People Struck with Aphasia

Similar lecture

Difficulty-Aware Machine Translation Evaluation

Stay up to date with the latest Underline news!

PRODUCT

COMPANY

RESOURCES

Downloads