We report on the design, fabrication, and characterization of an X-band 100-W Internally Matched FET (IMFET) designed for deployment in the Deep Space Antennas of the European Space Agency (ESA). The IMFET is based on high-voltage GaN dice, rated for a supply voltage of 100 V and serves as a feasibility study of a currently developed 200-W device, which is planned to be integrated into a 5-kW prototype amplifier system covering the antennas’ uplink band, ranging from 7.145 to 7.235 GHz. Measurements at a drain-source voltage of 70 V show an output power of more than 120 W at a power-added efficiency of 44.1% and a transducer gain higher than 15 dB, all reached at a compression level of 1 dB.

Text-editing models have recently become a prominent alternative to seq2seq models for monolingual text-generation tasks such as grammatical error correction, simplification, and style transfer. These tasks share a common trait -- they exhibit a large amount of textual overlap between the source and target texts. Text-editing models take advantage of this observation and learn to generate the output by predicting edit operations applied to the source sequence. In contrast, seq2seq models generate outputs word-by-word from scratch thus making them slow at inference time. Text-editing models provide several benefits over seq2seq models including faster inference speed, higher sample efficiency, and better control and explainability of the outputs. This tutorial provides a comprehensive overview of text-editing models and discusses how they can be used to mitigate hallucination and bias, both pressing challenges in the field of text generation. Finally, we discuss how to optimize latency of large language models via distillation to text-editing models and other means.

Eric Malmi, Sebastian Krause, Sascha Rothe, Daniil Mirylenka, Aliaksei Severyn. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Conversational agents offer users a naturallanguage interface to accomplish tasks, entertain themselves, or access information.Informational dialogue is particularly challenging in that the agent has to hold a conversation on an open topic, and to achieve a reasonable coverage it generally needs to digest and present unstructured information from textual sources.Making responses based on such sources sound natural and fit appropriately into the conversation context is a topic of ongoing research, one of the key issues of which is preventing the agent's responses from sounding repetitive.Targeting this issue, we propose a new task, known as redundancy localization, which aims to pinpoint semantic overlap between text passages.To help address it systematically, we formalize the task, prepare a public dataset with fine-grained redundancy labels, and propose a model utilizing a weak training signal defined over the results of a passage-retrieval system on web texts.The proposed model demonstrates superior performance compared to a state-of-the-art entailment model and yields encouraging results when applied to a real-world dialogue. * Work performed during an internship at Google.User: What is Malaria?Agent: A disease caused by a plasmodium parasite, transmitted by the bite of infected mosquitoes.User: Is it a virus?Agent: Malaria is a parasitic infection spread by Anopheles mosquitoes.The Plasmodium parasite that causes Malaria is neither a virus nor a bacterium -it is a single-celled parasite that multiplies in red blood cells of humans as well as in the mosquito intestine.

Coreference resolution for event mentions enables extraction systems to process document-level information.Current systems in this area base their decisions on rich semantic features from various knowledge bases, thus restricting them to domains where such external sources are available.We propose a model for this task which does not rely on such features but instead utilizes sentential features coming from convolutional neural networks.Two such networks first process coreference candidates and their respective context, thereby generating latent-feature representations which are tuned towards event aspects relevant for a linking decision.These representations are augmented with lexicallevel and pairwise features, and serve as input to a trainable similarity function producing a coreference score.Our model achieves state-of-the-art performance on two datasets, one of which is publicly available.An error analysis points out directions for further research.

Sebastian Krause, Enrique Alfonseca, Katja Filippova, Daniele Pighin. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2015.

The article demonstrates how generic parsers in a minimally supervised information extraction framework can be adapted to a given task and domain for relation extraction (RE). For the experiments, two parsers that deliver n-best readings are included: (1) a generic deep-linguistic parser (PET) with a largely hand-crafted head-driven phrase structure grammar for English (ERG); (2) a generic statistical parser (Stanford Parser) trained on the Penn Treebank. It will be shown how the estimated confidence of RE rules learned from the n-best parses can be exploited for parse reranking for both parsers. The acquired reranking model improves the performance of RE in both training and test phases with the new first parses. The obtained significant boost of recall does not come from an overall gain in parsing performance but from an application-driven selection of parses that are best suited for the RE task. Since the readings best suited for the successful extraction of rules and instances are often not the readings favoured by a regular parser evaluation, generic parsing accuracy actually decreases. The novel method for task-specific parse reranking does not require any annotated data beyond the semantic seed, which is needed anyway for the RE task.