Korea, Republic of

The Visual Dialogue (VD) task has recently received increasing attention in AI research. VD aims to generate multi-round, interactive responses based on the dialog history and image content. Existing textual dialogue models cannot fully understand visual information, resulting in a lack of scene features when communicating with humans continuously. Therefore, how to efficiently fuse multi-modal data features remains to be a challenge. In this work, we propose a knowledge transfer method with visual prompt (\textbf{VPTG}) fusing multi-modal data, which is a flexible module that can utilize the text-only seq2seq model to handle VD tasks. The VPTG conducts text-image co-learning and multi-modal information fusion with visual prompts and visual knowledge distillation. Specifically, we construct visual prompts from visual representations and then induce sequence-to-sequence (seq2seq) models to fuse visual information and textual contexts by visual-text patterns. Moreover, we also realize visual knowledge transfer through distillation between two different models&#39; text representations, so that the seq2seq model can actively learn visual semantic representations. Extensive experiments on the multi-modal dialogue understanding and generation (MDUG) datasets show the proposed VPTG outperforms other single-modal methods, which demonstrate the effectiveness of visual prompt and visual knowledge transfer.

COLING 2022

Knowledge Transfer with Visual Prompt in Multi-modal Dialogue Understanding and Generation

visual dialogue understanding and generation

prompt tuning

multimodal learning

[![](https://assets.underline.io/uploads/markdown_image/1/image/81a3c0317d24f663b49b996875024d45.png)](https://aclanthology.org/volumes/2022.coling-1/)



### THE CONFERENCE WE KNOW AND WE WANT.
**COLING**, the International Conference on Computational Linguistics, is one of the premier conferences for the natural language processing and computational linguistics.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes but also in industrial research departments including tech-startups. COLING provides opportunities for all these communities to showcase their exciting discovery.

In fall of 2022, COLING will be held in Gyeongju in a hybrid format. All participants can either present at the venue site or join virtually. As more people get vaccinated, we are happy to provide safer environments for our colleagues. We believe that COLING 2022 will be one of the conferences, free from the pandemic. The hybrid format gives presenters and sponsors a valuable opportunity to promote their companies in both an online and in-person venue. For the first time in a long time, customers can interact with their sponsor's products first-hand. The online venue, too, gives sponsors the chance to network with those unable to attend the in-person session.

The hybrid format ultimately lends itself to greater exposure for our sponsors: COLING2022 will let you reach more potential partners and customers than ever before!<br><br><br>

To gain access to this event page you are required to register.<br> Find more information and pay the registration fee on event the organizer’s website **[https://coling2022.org/reg](https://coling2022.org/reg)**

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for the natural language processing and computational linguistics.

The Visual Dialogue (VD) task has recently received increasing attention in AI research. VD aims to generate multi-round, interactive responses based on the dialog history and image content. Existing textual dialogue models cannot fully understand visual information, resulting in a lack of scene features when communicating with humans continuously. Therefore, how to efficiently fuse multi-modal data features remains to be a challenge. In this work, we propose a knowledge transfer method with visual prompt (\textbf{VPTG}) fusing multi-modal data, which is a flexible module that can utilize the text-only seq2seq model to handle VD tasks. The VPTG conducts text-image co-learning and multi-modal information fusion with visual prompts and visual knowledge distillation. Specifically, we construct visual prompts from visual representations and then induce sequence-to-sequence (seq2seq) models to fuse visual information and textual contexts by visual-text patterns. Moreover, we also realize visual knowledge transfer through distillation between two different models' text representations, so that the seq2seq model can actively learn visual semantic representations. Extensive experiments on the multi-modal dialogue understanding and generation (MDUG) datasets show the proposed VPTG outperforms other single-modal methods, which demonstrate the effectiveness of visual prompt and visual knowledge transfer.

workshop paper

Videos of group interactions contain a wealth of information beyond the information directly communicated in a transcript of the discussion. Tracking who has participated throughout an extended interaction and what each of their trajectories has been in relation to one another is the foundation for joint activity understanding, though it comes with some unique challenges in videos of tightly coupled group work. Motivated by insights into the properties of such scenarios, including group composition and the properties of task-oriented, goal-directed tasks, we present a successful proof-of-concept. In particular, we present a transfer experiment to a dyadic robot construction task, an ablation study, and a qualitative analysis.

Model Transfer for Event tracking as Transcript Understanding for Videos of Small Group Interaction

We present an empirical study investigating the influence of automatic speech recognition (ASR) errors on the spoken implicit discourse relation recognition (IDRR) task. We construct a spoken dataset for this task based on the Penn Discourse Treebank 2.0 (Prasad et al., 2008). On this dataset, we conduct “Cascaded” experiments employing state-of-the-art ASR and text-based IDRR models and find that the ASR errors significantly decrease the IDRR performance. In addition, the “Cascaded” approach does remarkably better than an “End-to-End”
one that directly predicts a relation label for each input argument speech pair.

Investigating the Impact of ASR Errors on Spoken Implicit Discourse Relation Recognition

One of the modern challenges in AI is the access to high-quality and annotated data, especially in NLP; that's why augmentation is gaining importance. In computer vision, where image data augmentation is standard, text data augmentation in NLP is complex due to the high complexity of language. And we have seen advantages of augmentation where there are fewer data available, and it can play a massive role in improving the model's accuracy and performance. We have implemented Augmentation in Pairwise sentence scoring in the biomedical domain.

By experimenting with our approach to downstream tasks on biomedical data, we have looked into the solution to improve Bi-encoders' sentence transformer performance using augmented data-set generated by cross-encoders fine-tuned on Biosses and MedNLI on pretrained Bio-BERT model. It has significantly improved the results with respect to the only the model only trained on Gold data for the respective tasks.

Augmented Bio-SBERT

This paper presents the usage of the RELATE platform (https://relate.racai.ro) for translation tasks involving the Romanian language. Using this platform, it is possible to perform text and speech data translations, either for single documents or for entire corpora. Furthermore, the platform was successfully used in international projects to create new resources useful for Romanian language translation.

Romanian language translation in the RELATE platform

Tokenization has been shown to impact the quality of downstream tasks, such as Neural Machine Translation (NMT), which is susceptible to out-of-vocabulary words and low frequency training data. Current state-of-the-art algorithms have been helpful in addressing the issues of out-of-vocabulary words, bigger vocabulary sizes and token frequency by implementing subword segmentation. We argue, however, that there is still room for improvement, in particular regarding low-frequency tokens in the training data. In this paper, we present "High Frequency Tokenizer", or HFT, a new language-independent subword segmentation algorithm that addresses this issue. We also propose a new metric to measure the frequency coverage of a tokenizer's vocabulary, based on a frequency rank weighted average of the frequency values of its items. We experiment with a diverse set of language corpora, vocabulary sizes, and writing systems and report improvements on both frequency statistics and on the average length of the output. We also observe a positive impact on downstream NMT.

HFT: High Frequency Tokens for Low-Resource NMT

Translating into low-resource languages is challenging due to the scarcity of training data. In this paper, we propose a probabilistic lexical translation method that bridges through lexical relations including synonyms, hypernyms, hyponyms, and co-hyponyms. This method, which only requires a dictionary like Wiktionary and a lexical database like WordNet, enables the translation of unknown vocabulary into low-resource languages for which we may only know the translation of a related concept. Experiments on translating a core vocabulary set into 472 languages, most of them low-resource, show the effectiveness of our approach.

Known Words Will Do: Unknown Concept Translation via Lexical Relations

Building a robust machine translation (MT) system requires a large amount of parallel corpus which is an expensive resource for low-resourced languages. The two major languages being spoken in the Philippines which are Filipino and Cebuano have an abundance in monolingual data that this study took advantage of attempting to find the best way to automatically generate parallel corpus out from monolingual corpora through the use of bitext alignment. Byte-pair encoding was applied in an attempt to optimize the alignment of the source and target texts. Results have shown that alignment was best achieved without segmenting the tokens. Itermax alignment score is best for short-length sentences and match or argmax alignment score are best for long-length sentences.

Exploring Word Alignment Towards an Efficient Sentence Aligner for Filipino and Cebuano Languages

Multilingual transfer techniques often improve low-resource machine translation (MT). Many of these techniques are applied without considering data characteristics. We show in the context of Haitian-to-English translation that transfer effectiveness is correlated with amount of training data and relationships between knowledge-sharing languages. Our experiments suggest that for some languages beyond a threshold of authentic data, back-translation augmentation methods are counterproductive, while cross-lingual transfer from a sufficiently related language is preferred. We complement this finding by contributing a rule-based French-Haitian orthographic and syntactic engine and a novel method for phonological embedding. When used with multilingual techniques, orthographic transformation makes statistically significant improvements over conventional methods. And in very low-resource Jamaican MT, code-switching with a transfer language for orthographic resemblance yields a 6.63 BLEU point advantage.

Data-adaptive Transfer Learning for Translation: A Case Study in Haitian and Jamaican

Language-agnostic sentence embeddings generated by pre-trained models such as LASER and LaBSE are attractive options for mining large datasets to produce parallel corpora for low-resource machine translation. We test LASERand LaBSE in extracting bitext for two related low-resource African languages: Luhya and Swahili. For this work, we created a new parallel set of nearly 8000 Luhya-English sentences, allowing a new zero-shot test of LASER and LaBSE. We find that LaBSE significantly outperforms LASER in both languages. Both LASER and LaBSE however perform poorly at zero-shot alignment on Luhya, achieving just 1.5% and 22.0% successful alignments respectively (P@1 score). We fine-tune the embeddings on a small set of parallel Luhya sentences and show significant gains, improving the LaBSE alignment accuracy to 53.3%. Further, restricting the dataset to sentence embedding pairs with cosine similarity above 0.7 yielded alignments with over 85% accuracy.

Very Low Resource Sentence Alignment: Luhya and Swahili

Neural Machine Translation (NMT) models are strong enough to convey semantic and syn- tactic information from the source language to the target language. However, these models are suffering from the need for a large amount of data to learn the parameters. As a result, for languages with scarce data, these models are at risk of underperforming. We propose to augment attention based neural network with reordering information to alleviate the lack of data. This augmentation improves the trans- lation quality for both English to Persian and Persian to English by up to 6% BLEU absolute over the baseline models.


Premium content

Knowledge Transfer with Visual Prompt in Multi-modal Dialogue Understanding and Generation

Downloads

Next from COLING 2022

Model Transfer for Event tracking as Transcript Understanding for Videos of Small Group Interaction

Similar lecture

Visual Prompt Tuning for Few-Shot Text Classification