More Like this

1. Metaphors Embedded in Chinese Characters Bridge Dissimilar Concepts

   Liu, Q.; Jing, S.; Lupyan, G. (July 2021, Proceedings of the Annual Meeting of the Cognitive Science Society, 43(43).)

   null (Ed.)

   How related is skin to a quilt or door to worry? Here, we show that linguistic experience strongly informs people’s judgments of such word pairs. We asked Chinese-speakers, English-speakers, and Chinese-English bilinguals to rate semantic and visual similarity between pairs of Chinese words and of their English translation equivalents. Some pairs were unrelated, others were also unrelated but shared a radical (e.g., “expert” and “dolphin” share the radical meaning “pig”), others also shared a radical which invokes a metaphorical relationship. For example, a quilt covers the body like skin; understand, with a sun radical, invokes understanding as illumination. Importantly, the shared radicals are not part of the pronounced word form. Chinese speakers rated word pairs with metaphorical connections as more similar than other pairs. English speakers did not even though they were sensitive to shared radicals. Chinese-English bilinguals showed sensitivity to the metaphorical connections even when tested with English words. 

   more » « less
2. X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents

   Moradshahi, Mehrad; Shen, Tianhao; Bali, Kalika; Choudhury, Monojit; de Chalendar, Gaël; Goel, Anmol; Kim, Sungkyun; Kodali, Prashant; Kumaraguru, Ponnurangam; Semmar, Nasredine; et al (July 2023, Findings of the Association for Computational Linguistics (ACL), Toronto, Canada, 2023)

   Task-oriented dialogue research has mainly focused on a few popular languages like English and Chinese, due to the high dataset creation cost for a new language. To reduce the cost, we apply manual editing to automatically translated data. We create a new multilingual benchmark, X-RiSAWOZ, by translating the Chinese RiSAWOZ to 4 languages: English, French, Hindi, Korean; and a code-mixed English- Hindi language. X-RiSAWOZ has more than 18,000 human-verified dialogue utterances for each language, and unlike most multilingual prior work, is an end-to-end dataset for building fully-functioning agents. The many difficulties we encountered in creating X-RiSAWOZ led us to develop a toolset to accelerate the post-editing of a new language dataset after translation. This toolset improves machine translation with a hybrid entity alignment technique that combines neural with dictionary-based methods, along with many automated and semi-automated validation checks. We establish strong baselines for X-RiSAWOZ by training dialogue agents in the zero- and few-shot settings where limited gold data is available in the target language. Our results suggest that our translation and post-editing methodology and toolset can be used to create new high-quality multilingual dialogue agents cost-effectively. Our dataset, 

   more » « less
3. Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR

   https://doi.org/10.18653/v1/2021.findings-acl.406  

   Chen, Junkun; Ma, Mingbo; Zheng, Renjie; Huang, Liang (January 2021, Proceedings of ACL 2021: Findings)

   Simultaneous speech-to-text translation is widely useful in many scenarios. The conventional cascaded approach uses a pipeline of streaming ASR followed by simultaneous MT, but suffers from error propagation and extra latency. To alleviate these issues, recent efforts attempt to directly translate the source speech into target text simultaneously, but this is much harder due to the combination of two separate tasks. We instead propose a new paradigm with the advantages of both cascaded and endto-end approaches. The key idea is to use two separate, but synchronized, decoders on streaming ASR and direct speech-to-text translation (ST), respectively, and the intermediate results of ASR guide the decoding policy of (but is not fed as input to) ST. During training time, we use multitask learning to jointly learn these two tasks with a shared encoder. En-toDe and En-to-Es experiments on the MuSTC dataset demonstrate that our proposed technique achieves substantially better translation quality at similar levels of latency. 

   more » « less
4. Guiding Large Language Models to Post-Edit Machine Translation with Error Annotations

   Ki, Dayeon; Carpuat, Marine; Duh, Kevin; Gomez, Helena; Bethard, Steven (June 2024, Association for Computational Linguistics)

   Machine Translation (MT) remains one of the last NLP tasks where large language models (LLMs) have not yet replaced dedicated supervised systems. This work exploits the complementary strengths of LLMs and supervised MT by guiding LLMs to automatically post-edit MT with external feedback on its quality, derived from Multidimensional Quality Metric (MQM) annotations. Working with LLaMA-2 models, we consider prompting strategies varying the nature of feedback provided and then fine-tune the LLM to improve its ability to exploit the provided guidance. Through experiments on Chinese-English, English-German, and English-Russian MQM data, we demonstrate that prompting LLMs to post-edit MT improves TER, BLEU and COMET scores, although the benefits of fine-grained feedback are not clear. Fine-tuning helps integrate fine-grained feedback more effectively and further improves translation quality based on both automatic and human evaluation. 

   more » « less
5. Gaps in the Lexicon Restrict Communication

   https://doi.org/10.1162/opmi_a_00089  

   Rissman, Lilia; Liu, Qiawen; Lupyan, Gary (January 2023, Open Mind)

   Abstract Across languages, words carve up the world of experience in different ways. For example, English lacks an equivalent to the Chinese superordinate noun tiáowèipǐn, which is loosely translated as “ingredients used to season food while cooking.” Do such differences matter? A conventional label may offer a uniquely effective way of communicating. On the other hand, lexical gaps may be easily bridged by the compositional power of language. After all, most of the ideas we want to express do not map onto simple lexical forms. We conducted a referential Director/Matcher communication task with adult speakers of Chinese and English. Directors provided a clue that Matchers used to select words from a word grid. The three target words corresponded to a superordinate term (e.g., beverages) in either Chinese or English but not both. We found that Matchers were more accurate at choosing the target words when their language lexicalized the target category. This advantage was driven entirely by the Directors’ use/non-use of the intended superordinate term. The presence of a conventional superordinate had no measurable effect on speakers’ within- or between-category similarity ratings. These results show that the ability to rely on a conventional term is surprisingly important despite the flexibility languages offer to communicate about non-lexicalized categories. 

   more » « less